Abrégé

A method for generating a subtitle, an electronic device, and a computer-readable storage medium are provided. The method includes the following. A song audio signal is extracted from target video data. A target song corresponding to the song audio signal and a time position of the song audio signal in the target song are determined. Lyric information corresponding to the target song is obtained, where the lyric information includes one or more lyrics, and the lyric information further includes a starting time and duration of each lyric and/or a starting time and duration of each word in each lyric. A subtitle is rendered in the target video data based on the lyric information and time position to obtain target video data with a subtitle.

Classes IPC  ?

• G11B 27/036 - Montage par insertion
• G06F 16/635 - Filtrage basé sur des données supplémentaires, p.ex. sur des profils d'utilisateurs ou de groupes
• G06T 7/70 - Détermination de la position ou de l'orientation des objets ou des caméras
• G06T 11/20 - Traçage à partir d'éléments de base, p.ex. de lignes ou de cercles
• G06T 11/60 - Edition de figures et de texte; Combinaison de figures ou de texte
• G10L 15/26 - Systèmes de synthèse de texte à partir de la parole
• G10L 25/18 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par le type de paramètres extraits les paramètres extraits étant l’information spectrale de chaque sous-bande
• G10L 25/57 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes spécialement adaptées pour un usage particulier pour comparaison ou différentiation pour le traitement des signaux vidéo

Abrégé

Provided is an audio synthesis method. Music score data of target music is acquired, wherein the music score data includes audio data identifiers and performance time information corresponding to a plurality of sub-audios, an instrumental timbre corresponding to each of the sub-audios being matched with a hearing-impaired hearing timbre; the sub-audios based on the audio data identifiers corresponding to each of the sub-audios is acquired; and a synthetic audio of the target music is generated by performing a fusion process on the sub-audios based on the performance time information corresponding to each of the sub-audios.

Classes IPC  ?

• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques

Abrégé

Provided is a method for classifying videos. The method comprises: acquiring a target audio and a corresponding target video comprising human body actions; determining, based on a human body action matching degree of each target frame in the target video relative to a corresponding reference frame in a reference video, a total human body action matching degree score of the target video relative to the reference video; determining, based on an audio matching degree of each target audio segment in the target audio relative to a corresponding reference audio segment in a reference audio of the reference video, a total audio matching degree score of the target audio relative to the reference audio; and determining, based on the total human body action matching degree score and the total audio matching degree, a comprehensive classification result.

Classes IPC  ?

• G06V 10/764 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant la classification, p.ex. des objets vidéo
• G06V 40/20 - Mouvements ou comportement, p.ex. reconnaissance des gestes

Abrégé

A method and an apparatus for generating a remix. The method comprises: obtaining at least two audios which are different singing versions of a same song: extracting, from each audio, a vocal signal and an instrumental signal to obtain a vocal set the vocal signal of each audio and a instrumental set comprising the instrumental signal of each audio: aligning tracks of all vocal signals in the vocal set based on reference rhythm information selected from rhythm information of all vocal signals in the vocal set, where all vocal signals having the aligned tracks serve as to-be-mixed vocal audios: determining an instrumental signal, of which a track is aligned with those of the to-be-mixed vocal audios, from the instrumental set as a to-be-mixed instrumental audio: and mixing the to-be-mixed vocal audios with the to-be-mixed instrumental audio to obtain the remix.

Classes IPC  ?

• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques

Abrégé

Disclosed in the embodiments of the present application are a dance movement generation method, a computer device, and a storage medium. The method comprises: acquiring an audio to be used for choreography, and extracting a plurality of audio clips from said audio; inputting the plurality of audio clips into a pre-trained encoding model to obtain a first movement feature for each audio clip among the plurality of audio clips; according to the first movement features, determining from among movement features of a plurality of dance movements pre-stored in a movement library second movement features similar to the first movement features; and inputting the second movement feature corresponding to each audio clip into a pre-trained decoding model to obtain a third movement feature, and determining dance movements for said audio according to the third movement feature. In this way, the dance movements can be automatically generated, thus meeting user requirements for automatic and intelligent dance movement generation, and improving the quality of the dance movements.

Classes IPC  ?

• G06F 16/40 - Recherche d’informations; Structures de bases de données à cet effet; Structures de systèmes de fichiers à cet effet de données multimédia, p.ex. diaporama comprenant des données d'image et d’autres données audio
• G06F 18/214 - Génération de motifs d'entraînement; Procédés de Bootstrapping, p.ex. ”bagging” ou ”boosting”

Abrégé

The present application relates to a panoramic-image processing method, and a computer device, a storage medium and a computer program product. The method comprises: performing deformable convolution processing on a panoramic image to be processed, so as to obtain a feature image of said panoramic image (S101); performing regression processing on the feature image, so as to obtain image transformation information of said panoramic image (S102); according to the image transformation information and corrected pixel positions of said panoramic image, obtaining mapped pixel positions, which are in the panoramic image and correspond to the corrected pixel positions, wherein the corrected pixel positions are represented as coordinate positions of pixels in a corrected image corresponding to said panoramic image (S103); and performing pixel correction on said panoramic image according to pixel information of the mapped pixel positions, so as to obtain the corrected image corresponding to said panoramic image (S104).

Classes IPC  ?

• G06T 5/00 - Amélioration ou restauration d'image

Abrégé

An audio processing method, an apparatus, a device and a medium are provided. The method includes: acquiring a to-be-processed humming audio and music information corresponding to the to-be-processed humming audio, the music information including note information and beat per minute information; determining chords corresponding to the to-be-processed humming audio based on the note information and the beat per minute information; generating an MIDI file corresponding to the to-be-processed humming audio based on the note information and the beat per minute information; generating a chord accompaniment audio corresponding to the to-be-processed humming audio based on the beat per minute information, the chords and a pre-acquired chord accompaniment parameter, the chord accompaniment parameter being a chord accompaniment generation parameter set by a user; and outputting the MIDI file and the chord accompaniment audio.

Classes IPC  ?

• G10H 1/38 - Accord
• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques

Abrégé

A method and apparatus for audio processing, an electronic device, and a computer-readable storage medium are provided in the present disclosure. The method includes: obtaining a target dry audio, and determining a beginning and ending time of each lyric word in the target dry audio; detecting a pitch of the target dry audio and a fundamental frequency during the beginning and ending time, and determining a current pitch name of the lyric word based on the fundamental frequency and the pitch; tuning up the lyric word by a first key interval to obtain a first harmony, and tuning up the lyric word by different second key intervals respectively to obtain different second harmonies; synthesizing the first harmony and the second harmonies to form a multi-track harmony; and mixing the multi-track harmony with the target dry audio to obtain a synthesized dry audio.

Classes IPC  ?

• G10L 21/003 - Changement de la qualité de la voix, p.ex. de la hauteur tonale ou des formants

Abrégé

An audio generation method, an audio generation device, and a storage medium are provided. The method includes: receiving an audio generation instruction input by a user, wherein the audio generation instruction is used to indicate a two-dimensional image that the user wants to embed into generated target audio; obtaining a target grayscale image of the two-dimensional image in response to the audio generation instruction; converting grayscale data of each pixel in the target grayscale image into frequency-domain data of each pixel in a spectrogram, to obtain a target spectrogram; and generating target audio corresponding to the target spectrogram by using the target spectrogram.

Classes IPC  ?

• G10L 25/18 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par le type de paramètres extraits les paramètres extraits étant l’information spectrale de chaque sous-bande
• G06T 5/00 - Amélioration ou restauration d'image

Abrégé

The present application relates to an audio processing method, a copyright reading method, a computer device, and a computer readable storage medium. The method comprises: acquiring a copyright information index feature corresponding to copyright information of an audio to be processed, the copyright information index feature being used for indexing, in a copyright database, the copyright information of said audio (S202); obtaining a digital watermark according to the copyright information index feature (S204); and embedding the digital watermark into said audio to obtain a target audio (S206).

Classes IPC  ?

• G06F 21/16 - Traçabilité de programme ou de contenu, p.ex. par filigranage

Abrégé

A pitch adjustment method and apparatus, and a computer storage medium are provided. the fundamental frequency sequence of the singing sound of the user is obtained, the pitch difference between each candidate melody file and the fundamental frequency sequence at each corresponding time point is calculated, and the sum of all pitch differences of each candidate melody file is calculated. The candidate melody file with the minimum sum is determined as the target melody file, and the pitch of the accompaniment file of the target song is adjusted according to the pitch difference between the target melody file and the original melody file of the target song.

Classes IPC  ?

• G10H 1/36 - Dispositions pour l'accompagnement
• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques

Abrégé

A method and an apparatus for evaluating voice quality are provided. In the method, a playback of a standard audio is recorded to obtain a to-be-evaluated signal. Then a first power spectrum of the to-be-evaluated signal on a critical frequency band is determined to obtain a first spectrogram. Then a second power spectrum of a reference signal corresponding to the standard audio on a critical frequency band is determined to obtain a second spectrogram, where the reference signal is a sampled signal corresponding to the standard audio. Then an image similarity between the first spectrogram and the second spectrogram is determined to obtain a voice quality score of the to-be-evaluated signal.

Classes IPC  ?

• G10L 25/60 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes spécialement adaptées pour un usage particulier pour comparaison ou différentiation pour mesurer la qualité des signaux de voix
• G06T 5/00 - Amélioration ou restauration d'image
• G06T 7/13 - Détection de bords
• G10L 21/10 - Transformation en information visible

Abrégé

An audio synthesis method, a device and a computer-readable storage medium. The method comprises: acquiring song audio to be processed and corresponding song information (S101); performing human voice separation processing on the song audio to be processed, so as to obtain human voice audio (S102); on the basis of the human voice audio, determining target timbre information from a plurality of pieces of candidate timbre information (S103); acquiring a text template, and on the basis of the text template and the song information, generating text to be processed (S104); on the basis of the target timbre information, performing audio synthesis processing on the text to be processed, so as to obtain audio to be synthesized (S105); and performing synthesis processing on the audio to be synthesized and the song audio to be processed, so as to obtain synthesized audio (S106). The quality of synthesized audio which is obtained by means of the method is not limited to the artificial broadcasting level, such that the quality of synthesized audio is higher, and the playing effect is better.

Classes IPC  ?

• G10L 13/02 - Procédés d'élaboration de parole synthétique; Synthétiseurs de parole
• G10L 13/033 - Procédés d'élaboration de parole synthétique; Synthétiseurs de parole Édition de voix, p.ex. transformation de la voix du synthétiseur

Abrégé

Embodiments of the present application provide a modeling method for a metaverse scene material, used for automatically generating an obtained object to be modeled into an object model which can be customized and edited by a user, so that the personalized requirements of the user is met while the material generation efficiency is improved. The method in the embodiments of the present application comprises: obtaining an image of an object to be modeled; performing edge detection on the object in the image to extract edge contour lines of the object in the image; performing vectorization processing on the edge contour lines of the object in the image to obtain an edge contour line vector graphic of the object in the image; and editing vector lines in the vector graphic and a closed region formed by the vector lines to obtain a model of the object in the image.

Classes IPC  ?

• G06T 17/00 - Modélisation tridimensionnelle [3D] pour infographie

Abrégé

A method for determining volume adjustment ratio information comprises acquiring a first singing audio and an original accompaniment audio corresponding to the first singing audio, wherein the first singing audio is a user singing audio; acquiring a first audio of a non-singing part in the first singing audio, and acquiring a loudness characteristic of the first audio; acquiring, in the original accompaniment audio, a second audio whose playback duration corresponds to a playback duration of the first audio, and acquiring a loudness characteristic of the second audio; and determining a ratio of the loudness characteristic of the first audio to the loudness characteristic of the second audio as adjustment ratio information for adjusting an accompaniment volume of the first singing audio.

Classes IPC  ?

• G10H 1/46 - Commande de la puissance
• G10H 1/36 - Dispositions pour l'accompagnement
• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques

Abrégé

A Midi music file generation method, a computer-readable storage medium and a terminal. The method comprises: acquiring music score data, a played musical instrument and a chord fingering method data table of music to be configured (S101); determining the number of sound tracks in a Midi music file according to the number of strings of the played musical instrument (S102); reading chords in the music score data, and calling a rhythm-type data table to determine played string numbers of the played musical instrument corresponding to the chords (S103); calling the chord fingering method data table to query a fingering method corresponding to the played string numbers (S104); determining a musical scale sequence corresponding to the fingering method (S105); and determining a playing mode of each beat in the musical scale sequence, and then writing the musical scale sequence and the corresponding playing modes into the sound tracks, so as to obtain the Midi music file (S106). The method facilitates a player in learning a playing mode of each chord, and stabilizing a playing speed according to a Midi music file.

Classes IPC  ?

• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques

Abrégé

Disclosed in the present application are a subtitle generation method, an electronic device, and a computer-readable storage medium. The method comprises: extracting a song audio signal from target video data; determining a target song corresponding to the song audio signal, and a corresponding time position of the song audio signal in the target song; acquiring lyrics information corresponding to the target song, wherein the lyrics information comprises one or more sentences of lyrics, and the lyrics information further comprises a starting time and the duration of each sentence of the lyrics, and/or a starting time and the duration of each word in each sentence of the lyrics; and rendering subtitles in the target video data on the basis of the lyrics information and the time position, so as to obtain target video data with subtitles. By means of the solution provided in the present application, subtitles can be automatically generated for short music videos, such that the generation efficiency of subtitles can be improved.

Classes IPC  ?

• H04N 5/268 - Distribution ou commutation du signal
• H04N 21/431 - Génération d'interfaces visuelles; Rendu de contenu ou données additionnelles
• H04N 21/488 - Services de données, p.ex. téléscripteur d'actualités

Abrégé

Disclosed in the embodiments of the present application are an accompaniment generation method, a device, and a storage medium. The accompaniment generation method comprises: obtaining an acapella signal set, wherein the acapella signal set comprises x acapella signals corresponding to a target song; generating a virtual sound signal on the basis of an acapella signal corresponding to each of N virtual three-dimensional space sound image positions, wherein the x acapella signals correspond to the N virtual three-dimensional space sound image positions, the N virtual three-dimensional space sound image positions are different, and each virtual three-dimensional space sound image position is allowed to correspond to one or more of the x acapella signals; merging the virtual sound signals in a virtual sound signal set to obtain a chorus acapella; and performing, according to a sound effect optimization rule, sound effect synthesis on the chorus acapella and background music of the target song to obtain an accompaniment of the target song. By using the present application, the stereo surround sound effect of the accompaniment can be realized.

Classes IPC  ?

• G10H 1/36 - Dispositions pour l'accompagnement
• G10H 1/10 - Circuits pour établir le contenu harmonique des sons en combinant des sons pour obtenir des effets de chœur, des effets célestes ou des effets d'ensemble

Abrégé

An image processing method, a device, and a readable storage medium. The method comprises: acquiring from a video stream an image to be processed; converting the image to be processed into a YUV format to obtain a first image, and extracting Y-channel data corresponding to the first image; generating, by using the Y-channel data, brightness correction parameters respectively corresponding to pixels of the first image; performing, by using the brightness correction parameters, gamma brightness correction on the Y-channel data respectively corresponding to the pixels to obtain corrected data; replacing the Y-channel data with the corrected data to obtain a second image, and converting the second image into an RGB format to obtain a processed image; inputting the processed image and a historical adjacent frame optimization image into an evaluation model to obtain an evaluation parameter used for representing a brightness difference between the processed image and the historical adjacent frame optimization image; and if it is determined that the evaluation parameter is not in a target range, determining the processed image as a brightness optimized image corresponding to the image to be processed. The method keeps the brightness of a video stream to be overall stable.

Classes IPC  ?

• G06T 5/00 - Amélioration ou restauration d'image

Abrégé

An audio synthesis method and apparatus, and a device and a computer-readable storage medium, which belong to the technical field of computers. The method comprises: acquiring music score data of target music, wherein the music score data comprises audio data identifiers and performance time information, which correspond to a plurality of pieces of sub-audio, and a musical instrument timbre corresponding to each piece of sub-audio matches a hearing impairment auditory timbre (201); acquiring the corresponding sub-audio on the basis of each audio data identifier (202); and on the basis of the performance time information corresponding to each piece of sub-audio, performing fusion processing on the pieces of sub-audio, so as to generate synthesized audio of the target music (203). A synthesized audio obtained on the basis of the method can be completely heard by a patient suffering from a hearing impairment, and a distortion situation does not occur, such that the patient suffering from the hearing impairment can hear smooth music, the listening experience of the patient suffering from the hearing impairment is good, and the quality of music heard by the patient suffering from the hearing impairment can be improved, thereby improving a listening effect.

Classes IPC  ?

• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques

Abrégé

A method for generating a musical score, a device, and a computer-readable storage medium. The method comprises: obtaining target audio (S101); generating a chromagram of the target audio corresponding to each pitch class, utilizing the chromagram to identify a chord of the target audio, and obtaining chord information (S102); performing mode detection on the target audio, and obtaining original key information (S103); performing rhythm detection on the target audio and obtaining the beats per minute (S104); performing identification on a beat type of each audio frame of the target audio, and determining an audio time signature on the basis of a correspondence relationship between a beat type and a time signature (S105); utilizing the chord information, the original key information, the beats per minute, and the audio time signature and performing musical score rendering, and obtaining a target musical score (S106). Data and information necessary for rendering a musical score are obtained by means of performing processing on target audio, then same are further used to render a target musical score; compared to a means of manual transcription, the present invention can efficiently generate an accurate musical score, and enables greater efficiency and accuracy in musical score generation.

Classes IPC  ?

• G10G 3/00 - Enregistrement de la musique sous forme de notation, p.ex. enregistrement du fonctionnement mécanique d'un instrument de musique
• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques
• G06N 3/08 - Méthodes d'apprentissage

Abrégé

The present application belongs to the technical field of the Internet. Disclosed are a method and system for performing microphone-connection chorusing, and a device and a storage medium. The method comprises: receiving first live-streaming multimedia data that is sent by a first terminal, and second live-streaming multimedia data that is sent by a second terminal, wherein the first live-streaming multimedia data carries an accompaniment playing progress; when the received second live-streaming multimedia data carries a delay label, deleting the second live-streaming multimedia data; and when the received second live-streaming multimedia data carries a non-singing label and an accompaniment playing progress, synthesizing the first live-streaming multimedia data and the second live-streaming multimedia data on the basis of the accompaniment playing progress carried in the second live-streaming multimedia data and the accompaniment playing progress carried in the first live-streaming multimedia data, so as to obtain synthesized live-streaming multimedia data. By means of the present application, the problem of incoherent singing of two live streamers at an audience terminal during microphone-connection chorusing can be solved.

Classes IPC  ?

• H04N 21/845 - Structuration du contenu, p.ex. décomposition du contenu en segments temporels
• H04N 21/4788 - Services additionnels, p.ex. affichage de l'identification d'un appelant téléphonique ou application d'achat communication avec d'autres utilisateurs, p.ex. discussion en ligne
• H04N 21/234 - Traitement de flux vidéo élémentaires, p.ex. raccordement de flux vidéo ou transformation de graphes de scènes MPEG-4
• H04N 21/439 - Traitement de flux audio élémentaires
• H04N 21/239 - Interfaçage de la voie montante du réseau de transmission, p.ex. établissement de priorité des requêtes de clients
• H04N 21/233 - Traitement de flux audio élémentaires
• H04N 21/44 - Traitement de flux élémentaires vidéo, p.ex. raccordement d'un clip vidéo récupéré d'un stockage local avec un flux vidéo en entrée ou rendu de scènes selon des graphes de scène MPEG-4

Abrégé

A method for recognizing a song, including: acquiring a target song segment and transforming the target song segment to generate a corresponding first spectrum map; generating a multi-dimensional first feature vector according to the first spectrum map and a preset neural network model; acquiring second feature vectors of pre-stored songs, wherein one pre-stored song is divided into a plurality of pre-stored song segments, one pre-stored song segment corresponds to one second feature vector, and the first feature vector and the second feature vectors have the same number of dimensions; calculating similarities between the first feature vector and the second feature vectors, and determining a maximum similarity; and determining that the target song segment and a pre-stored song corresponding to the maximum similarity are different versions of the same song in response to the maximum similarity being greater than a preset threshold.

Classes IPC  ?

• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques
• G06F 17/14 - Transformations de Fourier, de Walsh ou transformations d'espace analogues

Abrégé

A voiceprint recognition method, a singer authentication method, an electronic device and a storage medium. The voiceprint recognition method comprises: receiving a user audio and determining a target audio corresponding to the user audio; determining the user voiceprint similarity between the target audio and the user audio and the reference voiceprint similarity between the target audio and each of a plurality of reference audios; constructing a similarity distribution model according to the reference voiceprint similarity between the target audio and each of the plurality of reference audios, and determining a distribution position of the user voiceprint similarity in the similarity distribution model; and determining, according to the distribution position, whether voiceprint matching is achieved between the user audio and the target audio. The present application can determine, according to a dynamic standard, whether voiceprints match, thereby improving the accuracy of voiceprint recognition.

Classes IPC  ?

• G10L 17/00 - Identification ou vérification du locuteur

Abrégé

A method and device for processing a chorus audio, and a storage medium. The method comprises the following steps: obtaining acapella audios of a plurality of singers singing the same target song (S110); performing time alignment on the plurality of obtained acapella audios (S120), and performing virtual sound image positioning, so as to position the plurality of acapella audios onto the plurality of virtual sound images (S130); generating a chorus audio on the basis of the plurality of acapella audios after having undergone the virtual sound image positioning (S140); and when a lead singer audio based on the singing of the target song is obtained, synthesizing the lead singer audio, the chorus audio, and a corresponding accompaniment, and then outputting a chorus effect audio (S150). The plurality of virtual sound images surround human ears and the plurality of acapella audios are positioned onto the plurality of virtual sound images, so that the outputted chorus effect audio can have a sound field surround sound effect, effectively preventing an in-head effect caused by sound field gathering in the center of the head, and enabling the sound field to be wider.

Classes IPC  ?

• G10L 13/04 - Procédés d'élaboration de parole synthétique; Synthétiseurs de parole - Détails des systèmes de synthèse de la parole, p.ex. structure du synthétiseur ou gestion de la mémoire
• G10L 13/047 - Architecture des synthétiseurs de parole
• G10L 13/033 - Procédés d'élaboration de parole synthétique; Synthétiseurs de parole Édition de voix, p.ex. transformation de la voix du synthétiseur
• H04S 7/00 - Dispositions pour l'indication; Dispositions pour la commande, p.ex. pour la commande de l'équilibrage

Abrégé

Provided is a method for playing media data. The method includes: receiving a trigger instruction; generating a second count value based on a stored first count value and a preset algorithm, and storing the second count value to overwrite the first count value, wherein the second count value is different from the first count value; generating audio data carrying a pre-stored authority identifier and the second count value; and playing the audio data, wherein the audio data is configured to instruct a second terminal to acquire the authority identifier and the second count value carried in the audio data, and send the authority identifier and the second count value to a server, and the second terminal is a terminal that has received the audio data.

Classes IPC  ?

• H04N 21/439 - Traitement de flux audio élémentaires
• H04N 21/2387 - Traitement de flux en réponse à une requête de reproduction par un utilisateur final, p.ex. pour la lecture à vitesse variable ("trick play")
• H04N 21/258 - Gestion de données liées aux clients ou aux utilisateurs finaux, p.ex. gestion des capacités des clients, préférences ou données démographiques des utilisateurs, traitement des multiples préférences des utilisateurs finaux pour générer des données co
• H04N 21/41 - Structure de client; Structure de périphérique de client

Abrégé

Provided a method for playing audios. The method includes: acquiring vibration control information corresponding to a target audio, wherein at least one vibration period and vibration attribute information corresponding to the at least one vibration period are recorded in the vibration control information, and each vibration period corresponds to a beat period of a target percussive instrument in the target audio; synchronously playing the target audio and the vibration control information; and when any vibration period of the at least one vibration period is played, controlling a terminal to vibrate based on vibration attribute information corresponding to the vibration period.

Classes IPC  ?

• H04R 27/00 - Systèmes d'annonce en public
• G06F 3/16 - Entrée acoustique; Sortie acoustique
• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques
• G10L 19/00 - Techniques d'analyse ou de synthèse de la parole ou des signaux audio pour la réduction de la redondance, p.ex. dans les vocodeurs; Codage ou décodage de la parole ou des signaux audio utilisant les modèles source-filtre ou l’analyse psychoacoustique
• H04R 3/00 - Circuits pour transducteurs

Abrégé

Implementation of the disclosure provides an audio processing method, a device, a terminal and a computer-readable storage medium. The method can include the following. An audio to-be-matched and a reference audio are obtained. A frequency spectrum distribution of the audio to-be-matched and a frequency spectrum distribution of the reference audio are obtained. A target filter set for matching the audio to-be-matched with the reference audio is determined according to the frequency spectrum distribution of the audio to-be-matched and the frequency spectrum distribution of the reference audio. The target filter set is determined as a matching rule for the audio to-be-matched and the reference audio. An audio playing device is compensated by using the matching rule to adjust an audio playing effect of the audio playing device; and an audio is played through the compensated audio playing device.

Classes IPC  ?

• H04R 3/04 - Circuits pour transducteurs pour corriger la fréquence de réponse
• G10L 19/26 - Pré-filtrage ou post-filtrage

Abrégé

A method and an apparatus for virtual listening scene construction and a storage medium are provided. The method includes the following. Target audio is determined, where the target audio is used to characterize a sound feature in a target scene. A position of a sound source of the target audio is determined. Dual-channel audio of the target audio is obtained by performing audio-visual modulation on the target audio according to the position of the sound source, where the dual-channel audio of the target audio during simultaneous output is able to produce an effect that the target audio is from the position of the sound source. The dual-channel audio of the target audio is rendered into target music to produce an effect that the target music is played in the target scene.

Classes IPC  ?

• H04R 5/04 - Circuits
• H04S 7/00 - Dispositions pour l'indication; Dispositions pour la commande, p.ex. pour la commande de l'équilibrage

Abrégé

A method for accompaniment purity class evaluation and related devices are provided. Multiple first accompaniment data and a label corresponding to each of the multiple first accompaniment data are obtained, the label being used to indicate that corresponding first accompaniment data is pure instrumental accompaniment data or instrumental accompaniment data with background noise. An audio feature of each of the multiple first accompaniment data is extracted. Model training is performed according to the audio feature of each of the multiple first accompaniment data and the label corresponding to each of the multiple first accompaniment data, to obtain a neural network model for accompaniment purity class evaluation, a model parameter of the neural network model being determined according to an association relationship between the audio feature of each of the multiple first accompaniment data and the label corresponding to each of the multiple first accompaniment data.

Classes IPC  ?

• G10H 1/36 - Dispositions pour l'accompagnement
• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques

Abrégé

Disclosed is a method, an apparatus, and a device for transient noise detection. The method includes: obtaining an audio frame signal having a preset duration; performing wavelet decomposition on a first audio frame signal to obtain a first wavelet decomposition signal corresponding to the first audio frame signal; determining a first reference audio intensity value of a first sub-wavelet decomposition signal according to reference audio intensity values of all samples in the first sub-wavelet decomposition signal; determining energy distribution information of the first wavelet decomposition signal according to first reference audio intensity values of all sub-wavelet decomposition signals in the first wavelet decomposition signal; and determining a probability that the first audio frame signal is transient noise according to the energy distribution information of the first wavelet decomposition signal.

Classes IPC  ?

• G10L 19/025 - Détection de transitions ou d’attaques pour le changement de résolution temps/fréquence
• G10L 19/02 - Techniques d'analyse ou de synthèse de la parole ou des signaux audio pour la réduction de la redondance, p.ex. dans les vocodeurs; Codage ou décodage de la parole ou des signaux audio utilisant les modèles source-filtre ou l’analyse psychoacoustique utilisant l'analyse spectrale, p.ex. vocodeurs à transformée ou vocodeurs à sous-bandes
• G10L 25/18 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par le type de paramètres extraits les paramètres extraits étant l’information spectrale de chaque sous-bande
• G10L 25/21 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par le type de paramètres extraits les paramètres extraits étant l’information sur la puissance

Abrégé

An accompaniment classification method and apparatus is provided. The method includes the following. A first type of audio features of a target accompaniment is obtained (S301, S401). Data normalization is performed on each kind of audio features in the first type of audio features of the target accompaniment to obtain a first feature-set of the target accompaniment and the first feature-set is input into a first classification model for processing (S302, S402). A first probability value output by the first classification model for the first feature-set is obtained (S303, S403). An accompaniment category of the target accompaniment is determined to be a first category of accompaniments when the first probability value is greater than a first classification threshold (S404). The accompaniment category of the target accompaniment is determined to be other categories of accompaniments when the first probability value is less than or equal to the first classification threshold.

Classes IPC  ?

• G06F 16/65 - Groupement; Classement
• G10H 1/36 - Dispositions pour l'accompagnement

Abrégé

Provided is a method for extracting a video segment, including: acquiring a boundary value of content of a video, wherein the boundary value includes an upper boundary, a lower boundary, a left boundary, and a right boundary; acquiring a plurality of first segments by performing key frame segmentation on the video; detecting an upper boundary of subtitles in each of the plurality of first segments; detecting a face position in each of the plurality of first segments; selecting, from the plurality of first segments, a second segment in which the face position satisfies a preset condition; and acquiring a third segment without subtitles by cropping the second segment based on an upper boundary of subtitles in the second segment.

Classes IPC  ?

• G06V 20/40 - RECONNAISSANCE OU COMPRÉHENSION D’IMAGES OU DE VIDÉOS Éléments spécifiques à la scène dans le contenu vidéo
• G06V 40/16 - Visages humains, p.ex. parties du visage, croquis ou expressions

Abrégé

An audio mixing song generation method and apparatus, a device, and a storage medium. In this solution, the method comprises: acquiring song audios of at least two singing versions of a same song (S201); extracting human voice signals and accompaniment signals in each song audio to obtain a human voice set comprising at least two human voice signals and an accompaniment set comprising at least two accompaniment signals (S202); selecting reference rhythm information from rhythm information corresponding to each song audio, performing audio track alignment on all the human voice signals on the basis of the reference rhythm information, and using all the human voice signals subjected to audio track alignment as human voice audios to be performed audio mixing (S203); determining the accompaniment signals aligned with audio tracks of the human voice audios in the accompaniment set as accompaniment audios to be performed audio mixing (S204); and mixing said human voice audios with said accompaniment audios to obtain an audio mixing song (S205). More songs can be covered for audio mixing, all the human voice signals in each song audio are subjected to audio track alignment, and accompaniment signals aligned with audio tracks of the human voice signals are selected, so that the coordination and synchronization of elements such as lyrics and beat can be maintained, and the audio mixing effect is improved.

Classes IPC  ?

• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques
• G10L 21/007 - Changement de la qualité de la voix, p.ex. de la hauteur tonale ou des formants caractérisé par le procédé utilisé

Abrégé

An audio generating method and device. The method comprises: receiving an audio generating instruction input by a user (S101), the audio generating instruction being used for indicating a two-dimensional image that the user is intended to embed into a generated target audio; in response to the audio generating instruction, acquiring a target grayscale image of the two-dimensional image (S102) (S501) (S901); converting grayscale data of each pixel point in the target grayscale image into frequency domain data of each pixel point in a spectrogram to obtain a target spectrogram (S103); and generating a target audio corresponding to the target spectrogram by using the target spectrogram (S104) (S504) (S903). The purpose of embedding image information into an audio can be achieved, such that an image has a sound producing function, and in addition, because the audio can comprise the image information, the relevance between the audio and the image is greatly improved.

Classes IPC  ?

• G10L 13/08 - Analyse de texte ou génération de paramètres pour la synthèse de la parole à partir de texte, p.ex. conversion graphème-phonème, génération de prosodie ou détermination de l'intonation ou de l'accent tonique
• G10L 13/02 - Procédés d'élaboration de parole synthétique; Synthétiseurs de parole
• G06T 11/20 - Traçage à partir d'éléments de base, p.ex. de lignes ou de cercles

Abrégé

A method and a device for audio repair and a readable storage medium are provided. The method includes the following. Multiple audio frames are sequentially inputted into a cache module, where the cache module is sequentially composed of multiple processing units, and a processing unit located at a center of the multiple processing units is a center processing unit (201). At least one audio frame contained in the center processing unit is assigned as a target frame (202). A noise point presented as a short-term high-energy pulse in the target frame is detected according to audio characteristics of the multiple audio frames in the cache module (203). The target frame is repaired to remove the noise point in the target frame (204).

Classes IPC  ?

• G10L 21/0264 - Filtration du bruit caractérisée par le type de mesure du paramètre, p.ex. techniques de corrélation, techniques de passage par zéro ou techniques prédictives
• G10L 21/0208 - Filtration du bruit
• G10L 21/0216 - Filtration du bruit caractérisée par le procédé d’estimation du bruit
• G10L 21/0224 - Traitement dans le domaine temporel
• G10L 21/0232 - Traitement dans le domaine fréquentiel

Abrégé

A method and apparatus for detecting a valid voice signal and a non-transitory computer readable storage medium are provided. A first audio signal including at least one audio frame signal is obtained. Multiple wavelet decomposition signals respectively corresponding to the at least one audio frame signal are obtained. A wavelet signal sequence is obtained by combining the multiple wavelet decomposition signals. A maximum value and a minimum value among audio intensity values of all sample points are obtained, and a first audio intensity threshold is determined according to the maximum value and the minimum value. Sample points each having an audio intensity value greater than the first audio intensity threshold in the wavelet signal sequence are obtained, and a signal of sample points in the first audio signal corresponding to the sample points each having an audio intensity value greater than the first audio intensity threshold is determined as the valid voice signal.

Classes IPC  ?

• G10L 25/78 - Détection de la présence ou de l’absence de signaux de voix
• G10L 19/02 - Techniques d'analyse ou de synthèse de la parole ou des signaux audio pour la réduction de la redondance, p.ex. dans les vocodeurs; Codage ou décodage de la parole ou des signaux audio utilisant les modèles source-filtre ou l’analyse psychoacoustique utilisant l'analyse spectrale, p.ex. vocodeurs à transformée ou vocodeurs à sous-bandes
• G10L 25/21 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par le type de paramètres extraits les paramètres extraits étant l’information sur la puissance
• G10L 21/0272 - Séparation du signal de voix
• G10L 25/18 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par le type de paramètres extraits les paramètres extraits étant l’information spectrale de chaque sous-bande

Abrégé

Provided is a sound quality detection method, including: acquiring a plurality of audio files to be detected, wherein the plurality of audio files are homologous audio files; acquiring at least one audio feature of each of the plurality of audio files by performing feature extraction on the audio file, and generating a correspondence list between the at least one audio feature of each of the plurality of audio files and an audio file identifier; and determining, using a sound quality detection model, a sound quality score of each of the plurality of audio files based on the correspondence list between the at least one audio feature of each of the plurality of audio files and the audio file identifier, wherein the sound quality detection model is configured to detect sound quality of homologous audio files.

Classes IPC  ?

• G10L 19/16 - Architecture de vocodeur
• G10L 25/60 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes spécialement adaptées pour un usage particulier pour comparaison ou différentiation pour mesurer la qualité des signaux de voix
• G10L 25/48 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes spécialement adaptées pour un usage particulier
• G10L 25/51 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes spécialement adaptées pour un usage particulier pour comparaison ou différentiation
• G10L 19/24 - Codecs à débit variable, p.ex. pour générer différentes qualités en utilisant une représentation évolutive comme le codage hiérarchique ou le codage par couches
• G10L 19/18 - Vocodeurs utilisant des modes multiples

Abrégé

An online karaoke room implementation method, an electronic device, and a computer-readable storage medium. The method comprises: during a singing time period of a first account, a first client playing locally stored first audio content, and sending first target audio and progress information thereof to a second client, and the second client playing the first target audio; during a singing time period of a second account, the second client determining the current playing progress according to the received progress information, starting to play locally stored second audio content on the basis of the current playing progress, and sending second target audio and progress information thereof to the first client; and during the singing time period of the second account, if the first client receives the second target audio sent by the second client, playing the second target audio. By means of the online karaoke room implementation method provided by the present application, real-time antiphonal singing of multiple accounts is implemented.

Classes IPC  ?

• H04N 21/2187 - Transmission en direct
• H04N 21/233 - Traitement de flux audio élémentaires
• H04N 21/422 - Périphériques d'entrée uniquement, p.ex. système de positionnement global [GPS]
• H04N 21/432 - Opération de récupération de contenu d'un support de stockage local, p.ex. disque dur
• H04N 21/439 - Traitement de flux audio élémentaires
• H04N 21/4788 - Services additionnels, p.ex. affichage de l'identification d'un appelant téléphonique ou application d'achat communication avec d'autres utilisateurs, p.ex. discussion en ligne
• G06F 16/683 - Recherche de données caractérisée par l’utilisation de métadonnées, p.ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement utilisant des métadonnées provenant automatiquement du contenu
• G06F 16/68 - Recherche de données caractérisée par l’utilisation de métadonnées, p.ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement

Abrégé

The present application discloses a video classification method and apparatus, belonging to the technical field of data processing. The method comprises: acquiring a target audio and a corresponding target video comprising human body actions; on the basis of a human body action matching degree of each target frame in the target video with respect to a corresponding reference frame in a reference video, determining a total human body action matching degree score of the target video with respect to the reference video; on the basis of an audio matching degree of each target audio segment in the target audio with respect to a corresponding reference audio segment in a reference audio of the reference video, determining a total audio matching degree score of the target audio with respect to the reference audio; and on the basis of the total human body action matching degree score and the total audio matching degree, determining a comprehensive classification result. The present application provides a method for classifying singing and dancing videos.

Classes IPC  ?

• G06K 9/00 - Méthodes ou dispositions pour la lecture ou la reconnaissance de caractères imprimés ou écrits ou pour la reconnaissance de formes, p.ex. d'empreintes digitales
• G10L 25/51 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes spécialement adaptées pour un usage particulier pour comparaison ou différentiation

Abrégé

A method and device for obtaining a game prop, belonging to the technical field of games and multimedia. The method comprises: when a prop obtaining condition is met, a game client sending a prop obtaining request to a management side, wherein the obtaining request comprises an identifier of a target account, and the identifier of the target account is a game account identifier of a current login account (101); receiving a game prop to be used sent by the management side, wherein said game prop is determined according to the multimedia content corresponding to the identifier of the target account, and the multimedia content is generated by a multimedia platform (102); when a trigger instruction of said game prop is detected, executing a function corresponding to said game prop (103).

Classes IPC  ?

• A63F 13/71 - Aspects de sécurité ou de gestion du jeu utilisation d'une communication sécurisée entre les dispositifs de jeu et les serveurs de jeu, p.ex. en encryptant les données de jeu ou en authentifiant les joueurs

Abrégé

An audio processing method and apparatus, and an electronic device (30) and a medium. The method comprises: acquiring humming audio to be processed, so as to obtain music information corresponding to said humming audio (S11), wherein the music information comprises musical note information and beats-per-minute information; determining a chord corresponding to said audio on the basis of the musical note information and the beats-per-minute information (S12); generating, according to the musical note information and the beats-per-minute information, a MIDI file corresponding to said humming audio (S13); according to the beats-per-minute information, the chord and pre-acquired chord accompaniment parameters, generating chord accompaniment audio corresponding to said humming audio (S14); and outputting the MIDI file and the chord accompaniment audio (S15). Therefore, a melody rhythm and chord accompaniment audio corresponding to humming audio of a user can be generated, and cumulative errors are not prone to being generated, such that the music experiences of different users are consistent.

Classes IPC  ?

• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques
• G10H 1/36 - Dispositions pour l'accompagnement
• G10H 1/38 - Accord

Abrégé

An audio processing method and apparatus, an electronic device, and a computer-readable storage medium, the method comprising: acquiring a target dry audio, and determining the start and end time of each lyric word in the target dry audio (S101); detecting the pitch of the target dry audio and the fundamental frequency within the start and end time of each segment, and determining the current pitch name of each lyric word on the basis of the fundamental frequency and the pitch (S102); performing tone rising processing with a corresponding first cent span and a plurality of different second cent spans separately on each lyric word to obtain a first harmony and a plurality of different second harmonies, respectively, wherein the first cent span is a positive integer number of cents, the plurality of different second cent spans are the sum of the first cent span and a plurality of different third cent spans, and the first cent span and the third cent spans differ by an order of magnitude (S103); and synthesizing the first harmony and the plurality of different second harmonies to form a multi-track harmony, and mixing the multi-track harmony and the target dry audio to obtain a synthesized dry audio (S104). The audio processing method provided improves the hearing effect of dry audio.

Classes IPC  ?

• G10L 13/02 - Procédés d'élaboration de parole synthétique; Synthétiseurs de parole

Abrégé

A pitch adjustment method, which is used to automatically adjust the accompaniment of a target song, so that a user singing voice and the accompaniment match in pitch. The method comprises: acquiring a fundamental frequency sequence of a user singing voice (102); calculating a pitch value difference between each alternate melody file and the fundamental frequency sequence at each corresponding time point, and performing statistics on the sum of all pitch value differences for each alternate melody file separately (103); and determining that the alternate melody file that has the smallest sum is a target melody file, and adjusting the pitch of an accompaniment file of a target song according to the pitch value difference between the target melody file and an original melody file of the target song (104). Since the pitch identified by the target melody file has the highest matching degree with the pitch of the user singing voice, the accompaniment after pitch adjustment may match the pitch of the user singing voice, and the resulting mixed work may have a good sense of hearing. Also provided are a pitch adjustment device and a computer storage medium.

Classes IPC  ?

• G10H 1/36 - Dispositions pour l'accompagnement

Abrégé

A method and an apparatus for video frame processing are provided. The method includes: obtaining a convolutional neural network (CNN) feature and a local feature of a target video frame; performing dimension reduction on the CNN feature to obtain a CNN feature with a reduced dimension of the target video frame; obtaining a first video frame from multiple sample video frames, a distance between a CNN feature with a reduced dimension of the first video frame and the CNN feature with the reduced dimension of the target video frame meets a first preset condition; obtaining a local feature of the first video frame; calculating a matching degree between the local feature of the first video frame and the local feature of the target video frame; determining the first video frame as a duplicate video frame of the target video frame if the matching degree meets a second preset condition.

Classes IPC  ?

• G06V 20/40 - RECONNAISSANCE OU COMPRÉHENSION D’IMAGES OU DE VIDÉOS Éléments spécifiques à la scène dans le contenu vidéo
• G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
• G06V 10/74 - Appariement de motifs d’image ou de vidéo; Mesures de proximité dans les espaces de caractéristiques
• G06F 16/783 - Recherche de données caractérisée par l’utilisation de métadonnées, p.ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement utilisant des métadonnées provenant automatiquement du contenu

Abrégé

A sound quality evaluation method and apparatus, and an electronic device (20). The method comprises: performing recording during the playback of a standard audio to obtain a signal to be evaluated (S11, S21, S31); determining a first power spectrum, on a critical frequency band, of the signal to be evaluated to obtain a first spectrogram (S12, S23, S32); determining a second power spectrum, on the critical frequency band, of a reference signal corresponding to the standard audio to obtain a second spectrogram, the reference signal being a sampling signal corresponding to the standard audio (S13, S24, S33); and determining the image similarity between the first spectrogram and the second spectrogram to obtain a sound quality score of the signal to be evaluated (S14, S25, S35). That is to say, the image similarity is determined to further determine the similarity between the power spectrum on the critical frequency band of the signal to be evaluated and the reference signal to obtain the sound quality score of the signal to be evaluated, such that the complexity of a sound quality evaluation algorithm is lowered, thereby increasing the speed of sound quality evaluation, and the method has no requirement for the audio sampling rate.

Classes IPC  ?

• G10L 25/21 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par le type de paramètres extraits les paramètres extraits étant l’information sur la puissance
• G10L 25/60 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes spécialement adaptées pour un usage particulier pour comparaison ou différentiation pour mesurer la qualité des signaux de voix
• G06K 9/62 - Méthodes ou dispositions pour la reconnaissance utilisant des moyens électroniques
• G06T 5/00 - Amélioration ou restauration d'image
• G06T 7/13 - Détection de bords

Abrégé

A method for rendering lyrics is provided, including: acquiring pronunciation of a polyphonic word to be rendered in target lyrics, and acquiring playback time information of the pronunciation in the process of rendering the target lyrics; determining a first number of furiganas contained in the pronunciation; and word-by-word simultaneously rendering, according to the first number and the playback time information of the pronunciation of the polyphonic word to be rendered, the polyphonic word to be rendered and each furigana in the pronunciation of the polyphonic word to be rendered, wherein the pronunciation of the polyphonic word to be rendered is adjacent to and parallel to the polyphonic word to be rendered.

Classes IPC  ?

• G06F 40/169 - Annotation, p.ex. données de commentaires ou notes de bas de page
• G06F 40/279 - Reconnaissance d’entités textuelles

Abrégé

A method, apparatus and system for playing audio, and a device and a storage medium, belonging to the technical field of internet. The method comprises: acquiring vibration control information corresponding to target piece of audio, wherein at least one vibration time period and vibration attribute information corresponding to the at least one vibration time period are recorded in the vibration control information, and each vibration time period respectively corresponds to a striking time period of a target percussion instrument in the target piece of audio (101); synchronously playing the target piece of audio and the vibration control information (102); and when any of the at least one vibration time period is played, on the basis of the vibration attribute information corresponding to the any vibration time period, controlling a terminal to vibrate (103). By means of the present application, audio presentation manners can be diversified, and audio playing flexibility can be improved.

Classes IPC  ?

• G06F 3/01 - Dispositions d'entrée ou dispositions d'entrée et de sortie combinées pour l'interaction entre l'utilisateur et le calculateur

Abrégé

The embodiments of the present application disclose a virtual listening scene constructing method and a related device. Said method comprises: determining a target audio, the target audio being used for representing sound features in a target scene; determining the position of a sound source of the target audio; performing acoustic image modulation on the target audio according to the position of the sound source, so as to obtain a dual-channel audio of the target audio; and rendering the dual-channel audio of the target audio into target music, so as to obtain an effect of playing back the target music in the target scene. The listening scene constructing method provided by the embodiments of the present application provides an immersive listening experience for a user, such that the user can feel special scene elements lingering in the ears while enjoying music, enhancing the user's sense of immediacy.

Classes IPC  ?

• H04S 1/00 - Systèmes à deux canaux
• H04R 3/00 - Circuits pour transducteurs

Abrégé

An accompaniment classification method and device. Said method comprises: acquiring first-type audio features of a target accompaniment (S301, S401); performing data standardization processing on audio features in the first-type audio features of the target accompaniment, so as to obtain a first feature set of the target accompaniment, and inputting the first feature set into a first classification model for processing (S302, S402); acquiring a first probability value outputted by the first classification model for the first feature set (S303, S403); if the first probability value is greater than a first classification threshold, determining that the accompaniment category of the target accompaniment is an accompaniment of first type (S404), and if the first probability value is less than or equal to the first classification threshold, determining that the accompaniment category of the target accompaniment is an accompaniment of other types. Said method can rapidly and effectively classify the accompaniments, thereby improving the efficiency of accompaniment classification and reducing labor costs.

Classes IPC  ?

• G06F 16/65 - Groupement; Classement

Abrégé

The present application relates to the technical field of audio, and provided therein is a transient noise detection method, the method comprising: acquiring an audio frame signal having a preset duration; performing wavelet decomposition on the first audio frame signal to obtain a first wavelet decomposition signal corresponding to the first audio frame signal, the first wavelet decomposition signal comprising a plurality of sub-wavelet decomposition signals; determining first reference audio intensity values of the first sub-wavelet decomposition signals according to reference audio intensity values of all sample points in the first sub-wavelet decomposition signals; determining energy distribution information of the first wavelet decomposition signal according to the first reference audio intensity values of all of the sub-wavelet decomposition signals in the first wavelet decomposition signal; and determining, according to the energy distribution information of the first wavelet decomposition signal, a probability that the first audio frame signal is transient noise. In the implementation of the present embodiment, the accuracy of transient noise detection is improved by counting the sample points in a wavelet packet decomposition signal.

Classes IPC  ?

• G10L 19/02 - Techniques d'analyse ou de synthèse de la parole ou des signaux audio pour la réduction de la redondance, p.ex. dans les vocodeurs; Codage ou décodage de la parole ou des signaux audio utilisant les modèles source-filtre ou l’analyse psychoacoustique utilisant l'analyse spectrale, p.ex. vocodeurs à transformée ou vocodeurs à sous-bandes

Abrégé

A detection method and detection device (14) for an effective voice signal, and a device (15), the method comprising: acquiring a first audio signal of a preset duration, the first audio signal comprising at least one audio frame signal (100); performing wavelet decomposition on each audio frame signal to obtain a plurality of wavelet decomposition signals separately corresponding to each audio frame signal, each wavelet decomposition signal comprising a plurality of sample points and an audio intensity value of each sample point (101); according to a framing sequence of the audio frame signals in the first audio signal, splicing the wavelet decomposition signals corresponding to the respective audio frame signals to obtain a wavelet signal sequence (102); acquiring the maximum value and the minimum value among the audio intensity values of all sample points in the wavelet signal sequence, and determining a first audio intensity threshold according to the maximum value and the minimum value among the audio intensity values of all sample points in the wavelet signal sequence (103); and acquiring a sample point in the wavelet signal sequence the audio intensity value of which is greater than the first audio intensity threshold, and determining that the signal of a sample point in the first audio signal corresponding to the sample point in the wavelet signal sequence the audio intensity value of which is greater than the first audio intensity threshold value is an effective voice signal (104). The effective voice signal is determined and detected by means of collecting energy information of all sample points in the wavelet signal sequence, which improves the accuracy of effective voice detection.

Classes IPC  ?

• G10L 25/03 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par le type de paramètres extraits
• G10L 25/78 - Détection de la présence ou de l’absence de signaux de voix

Abrégé

A method for determining volume adjustment ratio information, an apparatus, a device and a storage medium, which belong to the technical field of the Internet. The method comprises: acquiring a first vocal audio and an original accompanying audio corresponding to the first vocal audio, wherein the first vocal audio is a user vocal audio (101); acquiring a non-vocal part of first audio from the first vocal audio, and acquiring the loudness feature of the first audio (102); acquiring a second audio corresponding to the first audio from the original accompanying audio during a playback period, and acquiring the loudness feature of the second audio (103); and determining the ratio of the loudness feature of the first audio to the loudness feature of the second audio to be adjustment ratio information of the first vocal audio for adjusting the accompanying volume (104). The described method captures corresponding first and second audios from user vocal audio and original accompanying audio to determine ratio information for adjusting the volume of the accompanying audio, which may improve the accuracy of the volume adjustment ratio information of the accompanying audio.

Classes IPC  ?

• G06F 3/16 - Entrée acoustique; Sortie acoustique

Abrégé

A method, apparatus and system for playing media data, and a device and a storage medium, relating to the technical field of computers. The method comprises: receiving a trigger instruction (401); generating a second count value on the basis of a stored first count value and a preset algorithm, and storing the second count value to overwrite the first count value (402); generating audio data carrying a pre-stored authority identifier and the second count value (403); and playing the audio data (404). The method can prevent the media data from being pirated by recording.

Classes IPC  ?

• G06F 16/64 - Navigation; Visualisation à cet effet

Abrégé

Disclosed are a song recognition method and apparatus, a storage medium and an electronic device. In the solution, a target song segment is acquired, and conversion processing is carried out on the target song segment, so that a first spectrum map is generated; a multi-dimensional first feature vector is generated according to the first spectrum map and a preset neural network model; second feature vectors of prestored songs are acquired; the similarities between the first feature vector and the second feature vectors are calculated, and the maximum similarity is determined; and if the maximum similarity is greater than a preset threshold value, it is determined that the target song segment and the prestored song corresponding to the maximum similarity are different versions of the same song, thereby improving the recognition accuracy for a cover song.

Classes IPC  ?

• G10L 25/54 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes spécialement adaptées pour un usage particulier pour comparaison ou différentiation pour la recherche
• G10L 25/30 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par la technique d’analyse utilisant des réseaux neuronaux
• G06F 16/683 - Recherche de données caractérisée par l’utilisation de métadonnées, p.ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement utilisant des métadonnées provenant automatiquement du contenu
• G06F 16/632 - Formulation de requêtes

Abrégé

Disclosed are a video clip extraction method and apparatus, a device and a storage medium, which belong to the technical field of multimedia. By means of the method, highlight clips can be automatically extracted from a video. A video is divided into a plurality of clips, a face is detected by means of facial detection, and an upper boundary of subtitles is detected by means of subtitle detection, such that a face position in a finally cut-out clip can meet a requirement; the subtitles of the video can be avoided, and the display effect is good; and tedious user operations are prevented, and the efficiency of clip extraction is improved.

Classes IPC  ?

• G06K 9/00 - Méthodes ou dispositions pour la lecture ou la reconnaissance de caractères imprimés ou écrits ou pour la reconnaissance de formes, p.ex. d'empreintes digitales

Abrégé

A video frame processing method and device. The video frame processing method comprises: acquiring a CNN feature of a target video frame and a local feature of the target video frame (S101); performing dimensionality reduction on the CNN feature of the target video frame, and obtaining a dimensionality-reduced CNN feature of the target video frame (S102); acquiring a first video frame from multiple sample video frames (S103), wherein a distance between a dimensionality-reduced CNN feature of the first video frame and the dimensionality-reduced CNN feature of the target video frame meets a first preset condition; acquiring a local feature of the first video frame (S104); calculating to obtain a degree of match between the local feature of the first video frame and the local feature of the target video frame (S105); and if the degree of match meets a second preset condition, taking the first video frame as a duplicate video frame of the target video frame (S106). The method and device can improve the accuracy of detecting a duplicate video frame.

Classes IPC  ?

• G06K 9/32 - Alignement ou centrage du capteur d'image ou de la zone image

Abrégé

An audio pop detection method and apparatus, and a storage medium. An audio signal to be detected can be obtained when performing pop detection on an audio signal, and the audio signal is divided into a plurality of frame signals (101); subsequently, the short-time energy difference between every two adjacent frame signals is calculated (102); then, frame signals satisfying a preset condition interval is obtained according to the short-term energy differences, to obtain a suddenly changed audio signal (103); and finally, spectral flatness of the suddenly changed audio signal is calculated, and if the spectral flatness is greater than a preset flatness value, it is determined that the audio signal has a pop (104). This solution can accurately determine whether an audio signal has a pop.

Classes IPC  ?

• G10L 25/78 - Détection de la présence ou de l’absence de signaux de voix

Abrégé

The present disclosure provides an online interaction method and device, belonging to the field of computer technology. Said method comprises: a server being able to receive a first request sent by a first terminal of a target room, the first request being used to instruct a microphone snatching request to be initiated, and then to send a first notification to terminals in the target room, the first notification being used to instruct microphone snatching processing to be performed; upon reception of second requests sent by the terminals, the server being able to determine a target number of terminals from the terminals sending the second requests, the second request being used to instruct a target song to be requested for singing, and then to send a second notification to the target number of terminals, the second notification being used to instruct the target song to be sung; and upon reception of audio and video data respectively sent by the target number of terminals, respectively sending the received audio and video data to the terminals in the target room except the target number of terminals. The present disclosure can achieve good interactivity.

Classes IPC  ?

• H04N 21/239 - Interfaçage de la voie montante du réseau de transmission, p.ex. établissement de priorité des requêtes de clients
• H04N 21/4788 - Services additionnels, p.ex. affichage de l'identification d'un appelant téléphonique ou application d'achat communication avec d'autres utilisateurs, p.ex. discussion en ligne
• H04N 21/472 - Interface pour utilisateurs finaux pour la requête de contenu, de données additionnelles ou de services; Interface pour utilisateurs finaux pour l'interaction avec le contenu, p.ex. pour la réservation de contenu ou la mise en place de rappels, pour la requête de notification d'événement ou pour la transformation de contenus affichés
• H04L 29/06 - Commande de la communication; Traitement de la communication caractérisés par un protocole

Abrégé

Embodiments of the present invention provide an audio processing method, a device, a terminal, and a computer-readable storage medium. The method can comprise: acquiring audio data awaiting matching and reference audio data; acquiring a frequency spectrum distribution of the audio data awaiting matching and a frequency spectrum distribution of the reference audio data; determining, according to the frequency spectrum distribution of the audio data awaiting matching and the frequency spectrum distribution of the reference audio data, a target filter set used to match the audio data awaiting matching to the reference audio data; using the target filter set from matching the audio data awaiting matching to the reference audio data as a matching rule; performing compensation on an audio playback apparatus by means of the matching rule, so as to adjust an audio playback effect of the audio playback apparatus; and playing audio data by means of the compensated audio playback apparatus. The present invention enables adaptive adjustment of an audio playback effect of an audio playback apparatus by using the matching rule, thereby improving efficiency in adjusting the audio playback effect.

Classes IPC  ?

• H04R 3/00 - Circuits pour transducteurs
• H04R 3/04 - Circuits pour transducteurs pour corriger la fréquence de réponse

Abrégé

Provided are a method for detecting tone quality of homologous audio, a device and storage medium, which belong to the technical field of audio. The method comprises: acquiring a plurality of audio files to be detected belonging to homologous audio files (101); extracting the features of each audio file of the plurality of audio files, to obtain at least one audio feature of each audio file, and to generate the corresponding relationship list between the at least one audio feature of each audio file and the audio file identifier (102); on the basis of the corresponding relationship list between the at least one audio feature of the plurality of audio file and the audio file identifier, determining the tone quality score of each audio file of the plurality of audio files through a tone quality detecting model (103). The tone quality detection of the homologous audio files is achieved, which is convenient to store, acquire and manage the homologous audio files according to the tone quality, and the storing, obtaining and managing costs of the homologous audio files can be saved.

Classes IPC  ?

• G10L 25/03 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par le type de paramètres extraits

Abrégé

Disclosed are an accompaniment purity evaluation method and a related device. The method comprises: obtaining multiple pieces of first accompaniment data and a tag corresponding to each piece of first accompaniment data, wherein the tag corresponding to each piece of first accompaniment data is used for indicating that the corresponding first accompaniment data is pure instrumental music accompaniment data or instrumental music accompaniment data having background noise; extracting the audio feature of each piece of first accompaniment data; and according to the audio feature of each piece of first accompaniment data and the tag corresponding to each piece of first accompaniment data, performing model training so as to obtain a neural network model used for accompaniment purity evaluation, wherein the model parameter of the neural network model is determined according to an association relationship between the audio feature of each piece of first accompaniment data and the tag corresponding to each piece of first accompaniment data. By implementing the embodiments of the present invention, the present invention can efficiently and accurately distinguish noise reduction accompaniment and original accompaniment.

Classes IPC  ?

• G10L 25/51 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes spécialement adaptées pour un usage particulier pour comparaison ou différentiation
• G10L 25/30 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par la technique d’analyse utilisant des réseaux neuronaux
• G10L 25/03 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par le type de paramètres extraits
• G10H 1/36 - Dispositions pour l'accompagnement

Abrégé

A multimedia data matching method and device, and a storage medium. The present application comprises: obtaining an audio data set to be matched; then analyzing multiple categories of each piece of audio data in the audio data set according to a preset strategy, and determining classification information of the audio data set according to the analysis result; next, analyzing the type of each image in a preset image library by means of a preset classification model, and determining classification information of each image according to the type of the image; and then, searching, on the basis of the classification information of the audio data set, the preset database for an image matching the classification information of the audio data set to obtain at least one matching image.

Classes IPC  ?

• G06F 16/432 - Formulation de requêtes

Abrégé

Disclosed are an audio repair method and device, and a readable storage medium. The method comprises: successively inputting a plurality of audio frames into a cache module, wherein the cache module is formed of a plurality of processing units in sequence, and a processing unit located at a central position of the plurality of processing units is a central processing unit (201); taking at least one audio frame included in the central processing unit as a target frame (202); detecting, according to audio features of the plurality of audio frames in the cache module, a noise point showing a short-term high-energy pulse in a target frame (203); and repairing the target frame, wherein the repair is used for removing the noise point in the target frame (204). According to the method, after a plurality of audio frames are continuously input into a cache module firstly, successively detecting and repairing noise points showing short-term high-energy pulses in the audio frames located at a central position of the cache module is an efficient, accurate and quick audio repair method.

Classes IPC  ?

• G10L 21/0208 - Filtration du bruit

Abrégé

An instrumental music detection method and apparatus, and a storage medium. The method comprises: acquiring audio to be tested (201); performing human voice separation processing on said audio to obtain an audio segment to be processed (202); then extracting audio features from said audio segment, the audio features comprising Mel features and human voice ratio features (203); inputting the audio features into a trained human voice detection network model (204); acquiring an output result of the trained human voice detection network model (205); and if determined, according to the output result, that said audio segment does not contain a human voice, then determining that said audio is instrumental music (206). The described method performs instrumental music detection on an audio segment separated from audio to be tested, without needing to perform detection on an entire song; the length of said audio is relatively short, and the method may improve the accuracy of instrumental music detection.

Classes IPC  ?

• G10L 25/78 - Détection de la présence ou de l’absence de signaux de voix

Abrégé

A method for calculating the number of syllables in a unit time and a related apparatus. The method comprises: obtaining a first audio segment comprising human voice and background music, and separating the human voice from the first audio segment to obtain a second audio segment comprising only human voice; inputting the second audio segment into a trained neural network model for processing, and outputting a first feature vector, the trained neural network model being used for extracting the feature vector of the audio segment of the human voice (101); determining, on the basis of the first feature vector, a target number of syllables corresponding to the second audio segment, and determining a target singing time corresponding to the second audio segment (102); and determining, on the basis of the target number of syllables and the target singing time, the number of syllables in a target unit time corresponding to the second audio segment (103). The number of syllables in the unit time of a song without lyric text can be calculated.

Classes IPC  ?

• G10L 21/0272 - Séparation du signal de voix
• G10L 25/30 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par la technique d’analyse utilisant des réseaux neuronaux

Abrégé

Disclosed are an audio recognition method, apparatus and device, and a storage medium. The method comprises: extracting an audio fingerprint of audio to be recognized to serve as a standard fingerprint, and calculating the similarity between the standard fingerprint and audio fingerprints in a pre-set fingerprint database (101); according to the similarity, screening out, from the fingerprint database, a candidate fingerprint set (102); selecting, from the candidate fingerprint set, a reference fingerprint, and acquiring a same-audio fingerprint of the reference fingerprint (103); and selecting, from audios corresponding to the reference fingerprint and to the same-audio fingerprint of the reference fingerprint, a target audio corresponding to the audio to be recognized (104).

Classes IPC  ?

• G10L 25/54 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes spécialement adaptées pour un usage particulier pour comparaison ou différentiation pour la recherche

Abrégé

A data processing method and apparatus, and a storage medium. The method comprises the following steps: acquiring, from a segment set, a header file segment for target multimedia data (S101); acquiring, according to the header file segment, absolute location information of respective data frames in the target multimedia data, determining, according to the absolute location information, relative location information of sub-segments corresponding to the respective data frames in the target multimedia data, and taking the relative location information of the sub-segments as information to be matched (S102); performing matching on the information to be matched and standard relative location information contained in all sub-segments in the segment set, and acquiring address information of the sub-segment containing the matched standard relative location information (S103); and generating multimedia segment indices corresponding to the target multimedia data according to an association relationship between the address information and the target multimedia data (S104). The method can reduce a probability of data loss, thereby enhancing data security.

Classes IPC  ?

• G06F 16/41 - Indexation; Structures de données à cet effet; Structures de stockage

Abrégé

An audio data processing method, characterized by comprising: acquiring dry audio data, calculating fundamental frequency reliability corresponding to the dry audio data, and determining a fundamental frequency of the dry audio data according to the fundamental frequency reliability (S101); acquiring a probability distribution of a non-zero fundamental frequency of the dry audio data, and determining a dominant fundamental frequency of the dry audio data according to the probability distribution (S102); selecting, according to the dominant fundamental frequency, target audio data from the dry audio data (S103); determining, according to the fundamental frequency of the target audio data, target harmonic energy corresponding to the target audio data (S104); determining first timbre quality data of the dry audio data according to the target harmonic energy, the first timbre quality data being used to measure the timbre of the dry audio data (S105). The present method objectively and accurately scores the timbre of dry audio data.

Classes IPC  ?

• G10L 25/03 - Techniques d'analyses de la parole ou de la voix qui ne se limitent pas à un seul des groupes caractérisées par le type de paramètres extraits

Abrégé

A method of playing audio data including: upon receiving a searching instruction of a target audio, displaying a video corresponding to an audio name of the target audio on a search result list; upon detection that the video corresponding to the audio name is being played, determining whether a background playing function is enabled; and when the background playing function is enabled, upon detection that an interface of playing the video is exited, making the video to continue being played in the background, that the video's picture is not displayed on a current screen. An apparatus of playing audio data and a computer-readable storage medium are further provided.

Classes IPC  ?

• G06F 3/16 - Entrée acoustique; Sortie acoustique
• G06F 21/51 - Contrôle des usagers, programmes ou dispositifs de préservation de l’intégrité des plates-formes, p.ex. des processeurs, des micrologiciels ou des systèmes d’exploitation au stade du chargement de l’application, p.ex. en acceptant, en rejetant, en démarrant ou en inhibant un logiciel exécutable en fonction de l’intégrité ou de la fiabilité de la source
• G06F 16/74 - Navigation; Visualisation à cet effet

Abrégé

Provided are a processing method, apparatus and device. The processing method comprises: acquiring a dry sound (S501), the dry sound comprising fundamental frequency data of a song sung by a user; acquiring timbre data of the dry sound (S502), with the timbre data being acquired by means of a pre-set training model; determining at least one sound effect scheme according to the acquired timbre data of the dry sound, a singing speed for a song associated with the dry sound and the fundamental frequency data (S503), with the sound effect scheme being used for carrying out sound effect processing on the dry sound and an accompaniment of the song associated with the dry sound so as to generate an audio subjected to sound effect processing; outputting at least one sound effect scheme (S504); and generating a target audio according to an acquired target sound effect scheme (S505), wherein the target sound effect scheme is a sound effect scheme in the at least one sound effect scheme. According to the processing method, the generated audio that is subjected to sound effect processing can be more pleasant.

Classes IPC  ?

• G10H 1/00 - INSTRUMENTS DE MUSIQUE ÉLECTROPHONIQUES; INSTRUMENTS DANS LESQUELS LES SONS SONT PRODUITS PAR DES MOYENS ÉLECTROMÉCANIQUES OU DES GÉNÉRATEURS ÉLECTRONIQUES, OU DANS LESQUELS LES SONS SONT SYNTHÉTISÉS À PARTIR D'UNE MÉMOIRE DE DONNÉES Éléments d'instruments de musique électrophoniques
• G10H 1/02 - Moyens pour contrôler la fréquence des sons, p.ex. attaque ou affaiblissement; Moyens pour produire des effets musicaux particuliers, p.ex. vibratos ou glissandos

Abrégé

Provided are an audio recognition method and device and a storage medium. The method comprises: obtaining an audio file and text information corresponding to the audio file, the text information comprising multiple characters (S101); setting each character in the text information as a target character sequentially and obtaining time information corresponding to the target character, the time information comprising start time and end time of the target character (S102); determining multiple start adjustment time corresponding to the target character according to the start time of the target character and determining multiple end adjustment time corresponding to the target character according to the end time of the target character (S103); and recognizing the audio file according to the multiple start adjustment time and the multiple end adjustment time of the target character so as to obtain pitch information of the target character (S104).

Classes IPC  ?

• G10L 25/90 - Détermination de la hauteur tonale des signaux de parole

Abrégé

A method and device for storing lyric phonetic notations, relating to the technical field of computers. The method comprises: a server can receive a phonetic notation storage request for a target lyric (101), and then obtain pronunciations of polyphonic characters in the target lyric, and determine the playback duration of furigana in the pronunciations of the polyphonic characters (102), obtain display information of the pronunciations of the polyphonic characters, the display information being used for indicating the playback time of the pronunciations of the polyphonic characters, finally correspondingly store the pronunciations of the polyphonic characters and the display information thereof with the target lyric (104). The method can improve the efficiency of displaying lyric phonetic notations.

Classes IPC  ?

• G06F 17/00 - TRAITEMENT ÉLECTRIQUE DE DONNÉES NUMÉRIQUES Équipement ou méthodes de traitement de données ou de calcul numérique, spécialement adaptés à des fonctions spécifiques

Abrégé

The present invention relates to the technical field of Internet, and provides a method and apparatus for generating lyrics, a method and apparatus for displaying lyrics, an electronic device, and a storage medium. The method comprises: acquiring lyrics of a target song; determining a character to be marked among a plurality of characters in the lyrics; querying, according to a word to which the character to be marked belongs and a preset query principle, the pronunciation of the character to be marked in the word, and determining the pronunciation of the character to be marked in the word as a corresponding pronunciation of the character to be marked in the target song; and generating a first lyric file of the target song according to the plurality of characters and the corresponding pronunciation of the character to be marked in the target song. Thus, the pronunciation can be displayed simultaneously during subsequent display of the lyrics, thereby ensuring that a user can sing the pronunciation of each character of the target song correctly. Moreover, when displaying the lyrics, the terminal can also mark the pronunciation above the corresponding character to be marked, so that the pronunciation is clear and distinct, thereby improving the accuracy of displaying the lyrics.

Classes IPC  ?

• G06F 16/00 - Recherche d’informations; Structures de bases de données à cet effet; Structures de systèmes de fichiers à cet effet

Abrégé

The present invention relates to the technical field of Internet. Disclosed are a method and an apparatus for generating lyrics, a method and an apparatus for displaying lyrics, an electronic device, and a storage medium. The method comprises: obtaining the lyrics of a target song and an audio file of the target song; determining, according to a character to be marked among a plurality of characters in the lyrics and audio segments corresponding to the plurality of characters in the audio file, a candidate pronunciation of said character to be marked; if said character has one candidate pronunciation, determining the candidate pronunciation as the corresponding pronunciation of said character in the target song; if said character has at least two candidate pronunciations, determining the candidate pronunciation semantically matching said character as the corresponding pronunciation of said character in the target song; and generating a first lyric file of the target song according to the plurality of characters and the corresponding pronunciation of said character to be marked in the target song, so that the pronunciation can be displayed simultaneously during the display of the lyrics, thereby ensuring that a user can sing the pronunciation of each character correctly.

Classes IPC  ?

• G06F 16/00 - Recherche d’informations; Structures de bases de données à cet effet; Structures de systèmes de fichiers à cet effet

Abrégé

A method and apparatus for processing a word bank, which fall within the field of computers. The method comprises: acquiring a first data record in a first word bank (101), wherein the first data record comprises a multi-character entry and a first kana set corresponding to each Chinese character in the multi-character entry, and the first kana set corresponding to the Chinese character comprises at least one kana corresponding to the Chinese character; searching a second word bank for a plurality of target data records corresponding to the first data record (102), wherein target entries in each target data record are different constituent parts of the multi-character entry, the target entries in each target data record form the multi-character entry, and a second kana set corresponding to each Chinese character in the target entries in the target data record is respectively the same as the first kana set corresponding to each Chinese character; and when the plurality of target data records corresponding to the first data record are not found in the second word bank, saving the first data record in the second word bank (103). The method can improve kana labelling efficiency.

Classes IPC  ?

• G06F 17/27 - Analyse automatique, p.ex. analyse grammaticale, correction orthographique

Abrégé

The present application relates to the technical field of computers and provides a method and device for rendering lyrics. The method comprises: obtaining the pronunciation of a polysyllabic word to be rendered in the target lyrics, and obtaining playback time information of the pronunciation in the process of rendering the target lyrics (201); determining a first number of pseudo-names comprised in the pronunciation (202); and performing, according to the first number and the playback time information of the pronunciation of the polysyllabic word to be rendered, word-for-word rendering on the polysyllabic word to be rendered and each pseudo-name in the pronunciation of the polysyllabic word to be rendered simultaneously (203), wherein the pronunciation of the polysyllabic word to be rendered is adjacent to and parallel to the polysyllabic word to be rendered. By means of the method, the lyrics rendering is more reasonable.

Classes IPC  ?

• G06F 16/34 - Navigation; Visualisation à cet effet

Abrégé

The present disclosure provides a method, a device, a computer readable storage medium for identifying and generating a graphic code, belonging to the field of graphic codes. The graphic code comprises a plurality of standard icons. The identification method comprises: obtaining a target image; identifying the position of a reference line in a graphic code in the target image, and identifying the positions of the standard icons in the graphic code; determining, according to the position of the reference line and the positions of the standard icons, relative positional information of each of the standard icons and the reference line; and on the basis of the relative positional information of each of the standard icons and the reference line, determining a coded string corresponding to the graphic code. The generation method comprises: generating a graphic code, wherein the graphic code comprises at least one reference line and a plurality of standard icons, the standard icons respectively satisfy relative positional relationships with the reference line, and the graphic code carries data information. The present disclosure provides a new type of graphic code different from bar codes or two-dimensional codes, such that the forms of graphic codes are enriched, and more attention can be attracted to the information carried by the graphic codes.

Classes IPC  ?

• G06K 7/14 - Méthodes ou dispositions pour la lecture de supports d'enregistrement par radiation corpusculaire utilisant la lumière sans sélection des longueurs d'onde, p.ex. lecture de la lumière blanche réfléchie
• G06K 19/06 - Supports d'enregistrement pour utilisation avec des machines et avec au moins une partie prévue pour supporter des marques numériques caractérisés par le genre de marque numérique, p.ex. forme, nature, code

Abrégé

The present application discloses a method and device for addition of song lyrics, pertaining to the field of information processing. The method comprises: receiving a lyrics addition instruction for a song accompaniment; searching for lyrics associated with the song accompaniment, and displaying a search result, wherein the search result comprises lyrics information of at least one song accompaniment; displaying lyrics data corresponding to target lyrics information on a lyrics editing interface according to a received selection operation for the target lyrics information in the search result; acquiring the lyrics data displayed on the lyrics editing interface; and when the song accompaniment is played, displaying the lyrics data. Even if lyrics corresponding to an accompaniment are not stored in a song recording application, the method of the present application allows a user to input selected lyrics data on the lyrics editing interface provided by the song recording application and allows the user to sing by referring to lyrics data displayed on the display interface, thereby improving the flexibility of accompaniment playing and song recording.

Classes IPC  ?

• G06F 17/30 - Recherche documentaire; Structures de bases de données à cet effet

Abrégé

The present disclosure relates to the technical field of computers and provides a method and apparatus for playing audio data. The method comprises: upon receipt of a searching instruction for a target audio, displaying a video corresponding to an audio name of the target audio in a searching result list; upon detection that the video corresponding to the audio name is being played, determining whether to enable a background playback function; if the background playback function is enabled, upon detection that an interface for playing the video is exited, controlling the video to continue to be played in the background, the video continuing to be played in the background referring to that a video picture of the video will not be displayed on a current screen. By means of the present disclosure, a lot of time can be saved.

Classes IPC  ?

• G06F 21/10 - Protection de programmes ou contenus distribués, p.ex. vente ou concession de licence de matériel soumis à droit de reproduction