42 - Services scientifiques, technologiques et industriels, recherche et conception
Produits et services
Providing on-line non-downloadable software for developing and operating artificial intelligence-based applications for planning, managing, analyzing and optimizing experimental workflows in the fields of materials science, chemistry, biology, life sciences, physics, drug development and advanced manufacturing; Application service provider featuring application programming interface (API) software for developing, training, fine-tuning, evaluating, deploying, executing, and running inference on artificial intelligence, machine-learning, foundation, multimodal, neural-network, computational physics, and unified scientific models for scientific research and development; Providing on-line non-downloadable software for developing, training, fine-tuning, evaluating, deploying, executing, and running inference on artificial intelligence, machine-learning, foundation, multimodal, neural-network, computational physics, and unified scientific models for scientific research and development; Providing on-line non-downloadable software for planning, managing, analyzing, and optimizing scientific research, experimental data, and experimental workflows; Providing on-line non-downloadable software for integrating artificial intelligence and computational models with automated laboratory equipment, robotic scientific instruments, and physical experimental apparatus; Research and development in the field of domain-specific and unified scientific AI models in the fields of physics, chemistry, biology, materials science, life sciences, engineering, and science; Research and development in the field of scientific AI foundation models, multimodal models, neural networks, computational models, and models that incorporate physical laws or scientific constraints; Research and development in the field of building scientific AI, machine-learning, foundation, and physics models for use in science, computational physics, materials science, chemistry, engineering, and advanced manufacturing; Scientific and technological services, namely, research, development, and consulting in the field of domain-specific and unified scientific AI models in the fields of physics, chemistry, biology, materials science, life sciences, engineering, and science; Scientific and technological services, namely, scientific research, development, and consulting in the field of scientific AI foundation models, multimodal models, neural networks, computational models, and models that incorporate physical laws or scientific constraints; Scientific and technological services, namely, scientific research, development and consulting in the field of building scientific AI, machine-learning, foundation, and physics models for use in science, computational physics, materials science, chemistry, engineering, and advanced manufacturing; Providing on-line non-downloadable software for developing, training, simulating, evaluating, and operating artificial intelligence and computational physics models for scientific research and development
09 - Appareils et instruments scientifiques et électriques
Produits et services
Downloadable electronic data files featuring artificial intelligence and machine-learning model files for predicting, simulating, or analyzing physical, chemical, biological, material, and other scientific systems; Downloadable electronic data files featuring electronic files containing the numerical parameters and weights of trained artificial intelligence and machine-learning models for predicting, simulating, or analyzing scientific systems;; Downloadable software for developing, training, fine-tuning, evaluating, deploying, executing, and running inference on artificial intelligence, machine-learning, foundation, multimodal, neural-network, computational physics, and unified scientific models for scientific research and development;; Downloadable software for planning, managing, analyzing, simulating, and optimizing scientific research, experimental data, and experimental workflows; Downloadable computer software for integrating artificial intelligence and computational models with automated laboratory equipment, robotic scientific instruments, and physical experimental apparatus; Downloadable software for software development kits for developing applications using artificial intelligence and computational models for scientific research and development
3.
METHOD FOR FORMING THE EXCITATION SIGNAL FOR A GLOTTAL PULSE MODEL BASED PARAMETRIC SPEECH SYNTHESIS SYSTEM
A method is presented for forming the excitation signal for a glottal pulse model based parametric speech synthesis system. In one embodiment, fundamental frequency values are used to form the excitation signal. The excitation is modeled using a voice source pulse selected from a database of a given speaker. The voice source signal is segmented into glottal segments, which are used in vector representation to identify the glottal pulse used for formation of the excitation signal. Use of a novel distance metric and preserving the original signals extracted from the speakers voice samples helps capture low frequency information of the excitation signal. In addition, segment edge artifacts are removed by applying a unique segment joining method to improve the quality of synthetic speech while creating a true representation of the voice quality of a speaker.
G10L 25/75 - Techniques d'analyse de la parole ou de la voix qui ne se limitent pas à un seul des groupes pour la modélisation des paramètres du conduit vocal
4.
METHOD FOR FORMING THE EXCITATION SIGNAL FOR A GLOTTAL PULSE MODEL BASED PARAMETRIC SPEECH SYNTHESIS SYSTEM
A method is presented for forming the excitation signal for a glottal pulse model based parametric speech synthesis system. In one embodiment, fundamental frequency values are used to form the excitation signal. The excitation is modeled using a voice source pulse selected from a database of a given speaker. The voice source signal is segmented into glottal segments, which are used in vector representation to identify the glottal pulse used for formation of the excitation signal. Use of a novel distance metric and preserving the original signals extracted from the speakers voice samples helps capture low frequency information of the excitation signal. In addition, segment edge artifacts are removed by applying a unique segment joining method to improve the quality of synthetic speech while creating a true representation of the voice quality of a speaker.
A system and method are presented for predicting contact center behavior. In one embodiment, closed form simulation modeling may be used to simulate behavior from input distributions. Models may be created through staging and analysis of historical Automatic Call Distribution data. Service level, average speed of answer, abandon rate, and other data may be predicted to generate forecasts and analysis of contact center behavior. Examples of behavior may include staffing levels, workload, and the Key Performance Index of metrics such as service level percentage, average speed of answer, and abandonment rate percentage.
G06Q 10/04 - Prévision ou optimisation spécialement adaptées à des fins administratives ou de gestion, p. ex. programmation linéaire ou "problème d’optimisation des stocks"
G06Q 10/0631 - Planification, affectation, distribution ou ordonnancement de ressources d’entreprises ou d’organisations
G06Q 10/0639 - Analyse des performances des employésAnalyse des performances des opérations d’une entreprise ou d’une organisation
6.
SYSTEM AND METHOD FOR PREDICTING CONTACT CENTER BEHAVIOR
A system and method are presented for predicting contact center behavior. In one embodiment, closed form simulation modeling may be used to simulate behavior from input distributions. Models may be created through staging and analysis of historical Automatic Call Distribution data. Service level, average speed of answer, abandon rate, and other data may be predicted to generate forecasts and analysis of contact center behavior. Examples of behavior may include staffing levels, workload, and the Key Performance Index of metrics such as service level percentage, average speed of answer, and abandonment rate percentage.
G06Q 10/04 - Prévision ou optimisation spécialement adaptées à des fins administratives ou de gestion, p. ex. programmation linéaire ou "problème d’optimisation des stocks"
G06Q 10/06 - Ressources, gestion de tâches, des ressources humaines ou de projetsPlanification d’entreprise ou d’organisationModélisation d’entreprise ou d’organisation
A system and method are presented for communication routing. Communications may be routed into a queue based on criteria. A communication may be assigned to a distribution ring and a determination may be made as to whether there is an availability of resources to handle the communication. A communication may be re-routed if it cannot be handled to a new group. Re-routing may be based on criteria such as time delay, non-time based criteria such as skills, and environmental criteria, to name a few. Re-routing may continue until a communication is handled. The routing design may resemble concentric circles where the center represents the most desirable pool of handlers and each incremental ring represents the iterative expansion sets of agents.
H04M 3/42 - Systèmes fournissant des fonctions ou des services particuliers aux abonnés
H04M 3/51 - Dispositions centralisées de réponse aux appels demandant l'intervention d'un opérateur
H04M 3/523 - Dispositions centralisées de réponse aux appels demandant l'intervention d'un opérateur avec répartition ou mise en file d'attente des appels
8.
SYSTEM AND METHOD FOR ROUTING A COMMUNICATION UTILIZING SCORING
A system and method are presented for routing a communication through monitoring one or more of words and voice characteristics of a communicant during an interaction. A communication may be handled based on a score. A score may be calculated based on several factors that are analyzed during an interaction, such as, amplitude, word usage, call metrics, etc. Previous interactions of communicants may also be factored into a score. Such handling may include specialized routing of the communication to a designated handler, for example. A communication may be continually evaluated during its occurrence and said evaluation data stored for future use.
A system and method are presented for context based knowledge retrieval. In one embodiment, such retrieval pertains to pattern recognition for data related to interactions between users, configuration and organization of systems data in an enterprise, and the quality of calculations of communication interactions. In one embodiment, a communication may be analyzed and a user interface created of potential sources of information related to the communication. This information may be from an internal source, such as a knowledge base, or an external source, such as an internet connected information source, for example. The user interface may comprise entities with associated links and actions, which may be configured based on a user's preference.
A system and method are presented for the encoding of participants in a conference setting. In an embodiment, audio from conference participants in a voice-over-IP setting may be received and processed by the system. In an embodiment, audio may be received in a compressed form and de-compressed for processing. For each participant, return audio is generated, compressed (if applicable) and transmitted to the participant. The system may recognize when participants are using the same audio encoding format and are thus receiving audio that may be similar or identical. The audio may only be encoded once instead of for each participant. Thus, redundant encodings are recognized and eliminated resulting in less CPU usage.
G10L 19/008 - Codage ou décodage du signal audio multi-canal utilisant la corrélation inter-canaux pour réduire la redondance, p. ex. stéréo combinée, codage d’intensité ou matriçage
G10L 21/003 - Changement de la qualité de la voix, p. ex. de la hauteur tonale ou des formants
11.
SYSTEM AND METHOD FOR PREDICTIVE LIVE INTERACTION OFFERING AND HOSTING
A system and method are presented for predictive live interaction offering and hosting. A mechanism may be provided for controlling outstanding offerings, or invitations, of communications with users through points of service. Offerings may include a live chat or a telephone callback request. In one embodiment, offerings may be optimized by analyzing factors such as agent history to predict when and how many agents will be available. Calculations may be continuously performed as invitations are accepted, declined, timed out, etc., to make certain more offers than can be handled are not extended.
A system and method are presented for relationship management workflow processes. At least one embodiment may apply to process automation to health care. More specifically, the system and method may be applied to patient management of healthcare, such as the management of Diabetes or other medical conditions. Other embodiments may apply to process automation in other areas utilizing management workflow software.
A system and method are presented for using spoken word verification to reduce false alarms by exploiting global and local contexts on a lexical level, a phoneme level, and on an acoustical level. The reduction of false alarms may occur through a process that determines whether a word has been detected or if it is a false alarm. Training examples are used to generate models of internal and external contexts which are compared to test word examples. The word may be accepted or rejected based on comparison results. Comparison may be performed either at the end of the process or at multiple steps of the process to determine whether the word is rejected.
A system and method are presented for using spoken word verification to reduce false alarms by exploiting global and local contexts on a lexical level, a phoneme level, and on an acoustical level. The reduction of false alarms may occur through a process that determines whether a word has been detected or if it is a false alarm. Training examples are used to generate models of internal and external contexts which are compared to test word examples. The word may be accepted or rejected based on comparison results. Comparison may be performed either at the end of the process or at multiple steps of the process to determine whether the word is rejected.
A system and method are presented for self-service callback modification. A user may request a callback. A unique confirmation identifier may be issued which may be used by the system to look up the callback record. A user may modify their callback request at any time during the callback process to receive their callback at a requested point in time, change the address to which the callback is addressed, alter the media through which the callback is placed, etc. Modification may occur in real time. Confirmation may be sent to the user after modification.
A system and method are presented for acoustic echo cancellation. The echo canceller performs reduction of acoustic and hybrid echoes which may arise in a situation such as a long-distance conference call with multiple speakers in varying environments, for example. Echo cancellation, in at least one embodiment, may be based on similarity measurement, statistical determination of echo cancellation parameters from historical values, frequency domain operation, double talk detection, packet loss detection, signal detection, and noise subtraction.
H04B 3/23 - Réduction des effets d'échos ou de sifflementSystèmes à ligne de transmission Détails ouverture ou fermeture de la voie d'émissionCommande de la transmission dans une direction ou l'autre utilisant une reproduction du signal transmis décalée dans le temps, p. ex. par dispositif d'annulation
H04M 9/08 - Systèmes téléphoniques à haut-parleur à double sens comportant des moyens pour conditionner le signal, p. ex. pour supprimer les échos dans l'une ou les deux directions du trafic
A system and method are presented for acoustic echo cancellation. The echo canceller performs reduction of acoustic and hybrid echoes which may arise in a situation such as a long-distance conference call with multiple speakers in varying environments, for example. Echo cancellation, in at least one embodiment, may be based on similarity measurement, statistical determination of echo cancellation parameters from historical values, frequency domain operation, double talk detection, packet loss detection, signal detection, and noise subtraction.
G10K 11/178 - Procédés ou dispositifs de protection contre le bruit ou les autres ondes acoustiques ou pour amortir ceux-ci, en général utilisant des effets d'interférenceMasquage du son par régénération électro-acoustique en opposition de phase des ondes acoustiques originales
G10L 21/0232 - Traitement dans le domaine fréquentiel
H04B 3/23 - Réduction des effets d'échos ou de sifflementSystèmes à ligne de transmission Détails ouverture ou fermeture de la voie d'émissionCommande de la transmission dans une direction ou l'autre utilisant une reproduction du signal transmis décalée dans le temps, p. ex. par dispositif d'annulation
H04M 3/56 - Dispositions pour connecter plusieurs abonnés à un circuit commun, c.-à-d. pour permettre la transmission de conférences
A system and method are presented for acoustic echo cancellation. The echo canceller performs reduction of acoustic and hybrid echoes which may arise in a situation such as a long-distance conference call with multiple speakers in varying environments, for example. Echo cancellation, in at least one embodiment, may be based on similarity measurement, statistical determination of echo cancellation parameters from historical values, frequency domain operation, double talk detection, packet loss detection, signal detection, and noise subtraction.
H04M 9/08 - Systèmes téléphoniques à haut-parleur à double sens comportant des moyens pour conditionner le signal, p. ex. pour supprimer les échos dans l'une ou les deux directions du trafic
A system and method are presented for learning call analysis. Audio fingerprinting may be employed to identify audio recordings that answer communications. In one embodiment, the system may generate a fingerprint of a candidate audio stream and compare it against known fingerprints within a database. The system may also search for a speech-like signal to determine if the end point contains a known audio recording. If a known audio recording is not encountered, a fingerprint may be computed for the contact and the communication routed to a human for handling. An indication may be made as to if the call is indeed an audio recording. The associated information may be saved and used for future identification purposes.
ABSTRACT A method is presented for routing communications in a communication system. Audio fingerprinting may be employed to identify audio recordings that answer communications. In one embodiment, the method may generate a fingerprint of a candidate audio stream and compare it against known fingerprints within a database. The method may also search for a speech-like signal to determine if the end point contains a known audio recording. If a known audio recording is not encountered, a fingerprint may be computed for the contact and the communication routed to a human for handling. An indication may be made as to if the call is indeed an audio recording. The associated information may be saved and used for future identification purposes. 17 Date Recue/Date Received 2020-10-01
A system and method are presented for learning call analysis. Audio fingerprinting may be employed to identify audio recordings that answer communications. In one embodiment, the system may generate a fingerprint of a candidate audio stream and compare it against known fingerprints within a database. The system may also search for a speech-like signal to determine if the end point contains a known audio recording. If a known audio recording is not encountered, a fingerprint may be computed for the contact and the communication routed to a human for handling. An indication may be made as to if the call is indeed an audio recording. The associated information may be saved and used for future identification purposes.
G10L 15/04 - SegmentationDétection des limites de mots
H04M 1/64 - Dispositions automatiques pour répondre aux appelsDispositions automatiques pour enregistrer des messages pour abonnés absentsDispositions pour enregistrer des conversations
22.
METHOD AND SYSTEM FOR PREDICTING SPEECH RECOGNITION PERFORMANCE USING ACCURACY SCORES
A system and method are presented for predicting speech recognition performance using accuracy scores in speech recognition systems within the speech analytics field. A keyword set is selected. Figure of Merit (FOM) is computed for the keyword set. Relevant features that describe the word individually and in relation to other words in the language are computed. A mapping from these features to FOM is learned. This mapping can be generalized via a suitable machine learning algorithm and be used to predict FOM for a new keyword. In at least embodiment, the predicted FOM may be used to adjust internals of speech recognition engine to achieve a consistent behavior for all inputs for various settings of confidence values.
ABSTRACT A method is presented for call learning in a communication system. Audio fingerprinting may be employed to identify audio recordings that answer communications. In one embodiment, the system may generate a fingerprint of a candidate audio stream and compare it against known fingerprints within a database. The system may also search for a speech-like signal to determine if the end point contains a known audio recording. If a known audio recording is not encountered, a fingerprint may be computed for the contact and the communication routed to a human for handling. An indication may be made as to if the call is indeed an audio recording. The associated information may be saved and used for future identification purposes. 19 Date Recue/Date Received 2020-10-01
A system and method are presented for predicting speech recognition performance using accuracy scores in speech recognition systems within the speech analytics field. A keyword set is selected. Figure of Merit (FOM) is computed for the keyword set. Relevant features that describe the word individually and in relation to other words in the language are computed. A mapping from these features to FOM is learned. This mapping can be generalized via a suitable machine learning algorithm and be used to predict FOM for a new keyword. In at least embodiment, the predicted FOM may be used to adjust internals of speech recognition engine to achieve a consistent behavior for all inputs for various settings of confidence values.
A system and method are presented for selectively biased linear discriminant analysis in automatic speech recognition systems. Linear Discriminant Analysis (LDA) may be used to improve the discrimination between the hidden Markov model (HMM) tied-states in the acoustic feature space. The between-class and within-class covariance matrices may be biased based on the observed recognition errors of the tied-states, such as shared HMM states of the context dependent tri-phone acoustic model. The recognition errors may be obtained from a trained maximum-likelihood acoustic model utilizing the tied-states which may then be used as classes in the analysis.
A system and method are presented for selectively biased linear discriminant analysis in automatic speech recognition systems. Linear Discriminant Analysis (LDA) may be used to improve the discrimination between the hidden Markov model (HMM) tied-states in the acoustic feature space. The between-class and within-class covariance matrices may be biased based on the observed recognition errors of the tied-states, such as shared HMM states of the context dependent tri-phone acoustic model. The recognition errors may be obtained from a trained maximum-likelihood acoustic model utilizing the tied-states which may then be used as classes in the analysis.
A system and method are presented for acoustic data selection of a particular quality for training the parameters of an acoustic model, such as a Hidden Markov Model and Gaussian Mixture Model, for example, in automatic speech recognition systems in the speech analytics field. A raw acoustic model may be trained using a given speech corpus and maximum likelihood criteria. A series of operations are performed, such as a forced Viterbi-alignment, calculations of likelihood scores, and phoneme recognition, for example, to form a subset corpus of training data. During the process, audio files of a quality that does not meet a criterion, such as poor quality audio files, may be automatically rejected from the corpus. The subset may then be used to train a new acoustic model.
G10L 15/06 - Création de gabarits de référenceEntraînement des systèmes de reconnaissance de la parole, p. ex. adaptation aux caractéristiques de la voix du locuteur
28.
METHOD AND SYSTEM FOR REAL-TIME KEYWORD SPOTTING FOR SPEECH ANALYTICS
A system and method are presented for real-time speech analytics in the speech analytics field. Real time audio is fed along with a keyword model, into a recognition engine. The recognition engine computes the probability of the audio stream data matching keywords in the keyword model. The probability is compared to a threshold where the system determines if the probability is indicative of whether or not the keyword has been spotted. Empirical metrics are computed and any false alarms are identified and rejected. The keyword may be reported as found when it is deemed not to be a false alarm and passes the threshold for detection.
A method and system for increasing call yield and the productivity of agents in an environment such as a contact or call center, for example, is described. Attributes may be used to classify calls and contact information. A system may iearn from collected data. Calculations may be performed to aid in forecasting such as probabilities, call yield, and expected call handle time. Such calculations may be used to determine the best time to call a contact to achieve a desired result.
A system and method are presented for negative example based performance improvements for speech recognition. The presently disclosed embodiments address identified false positives and the identification of negative examples of keywords in an Automatic Speech Recognition (ASR) system. Various methods may be used to identify negative examples of keywords. Such methods may include, for example, human listening and learning possible negative examples from a large domain specific text source. In at least one embodiment, negative examples of keywords may be used to improve the performance of an ASR system by reducing false positives.
Systems and methods for the matching of datasets, such as input audio segments, with known datasets in a database are disclosed. In an illustrative embodiment, the use of the presently disclosed systems and methods is described in conjunction with recognizing known network message recordings encountered during an outbound telephone call. The methodologies include creation of a ternary fingerprint bitmap to make the comparison process more efficient. Also disclosed are automated methodologies for creating the database of known datasets from a larger collection of datasets.
Systems and methods for the matching of datasets, such as input audio segments, with known datasets in a database are disclosed. In an illustrative embodiment, the use of the presently disclosed systems and methods is described in conjunction with recognizing known network message recordings encountered during an outbound telephone call. The methodologies include creation of a ternary fingerprint bitmap to make the comparison process more efficient. Also disclosed are automated methodologies for creating the database of known datasets from a larger collection of datasets.
A communication system including a media server through which communication packets are exchanged for recording and monitoring purposes is disclosed. A tap is associated with each communication endpoint allowing for cradle to grave recording of communications despite their subsequent routing or branching. An incoming communication is routed to a first tap and upon selection of a receiving party; the first tap is routed to a second tap which forwards communication packets on to the receiving party. The taps may be used to forward communication packets to any number of other taps or destinations, such as a recording device, monitoring user, or other user in the form of a conference.
H04L 12/28 - Réseaux de données à commutation caractérisés par la configuration des liaisons, p. ex. réseaux locaux [LAN Local Area Networks] ou réseaux étendus [WAN Wide Area Networks]
