At&t Intellectual Property I, LP

Nuance Communications, Inc.

Google Inc.

Diamantino Antonio Caseiro

Andrej Ljolje

Mazin E Gilbert

Alistair D Conkie

Enrico Bocchieri

Srinivas Bangalore

Patrick Guy Haffner

Taniya Mishra

Fadi Biadsy

Robert Bell

Vincent Goffin

Dimitrios Dimitriadis

Cyril Allauzen

Patrick Maxim Rondon

A method includes receiving context biasing data that includes a set of unspoken textual utterances corresponding to a particular context. The method also includes obtaining a list of carrier phrases associated with the particular context. For each respective unspoken textual utterance, the method includes generating a corresponding training data pair that includes the respective unspoken textual utterance and a carrier phrase. For each respective training data pair, the method includes tokenizing the respective training data pair into a sequence of sub-word units, generating a first higher order textual feature representation for a corresponding sub-word unit, receiving the first higher order textual feature representation, and generating a first probability distribution over possible text units. The method also includes training a speech recognition model based on the first probability distribution over possible text units.

Contextual biasing with text injection

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for language models using domain-specific model components. In some implementations, context data for an utterance is obtained. A domain-specific model component is selected from among multiple domain-specific model components of a language model based on the non-linguistic context of the utterance. A score for a candidate transcription for the utterance is generated using the selected domain-specific model component and a baseline model component of the language model that is domain-independent. A transcription for the utterance is determined using the score the transcription is provided as output of an automated speech recognition system.

Language models using domain-specific model components

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating domain-specific speech recognition models for a domain of interest by combining and tuning existing speech recognition models when a speech recognizer does not have access to a speech recognition model for that domain of interest and when available domain-specific data is below a minimum desired threshold to create a new domain-specific speech recognition model. A system configured to practice the method identifies a speech recognition domain and combines a set of speech recognition models, each speech recognition model of the set of speech recognition models being from a respective speech recognition domain. The system receives an amount of data specific to the speech recognition domain, wherein the amount of data is less than a minimum threshold to create a new domain-specific model, and tunes the combined speech recognition model for the speech recognition domain based on the data.

System and method for rapid customization of speech recognition models

Disclosed herein are methods, systems, and computer-readable storage media for automatic speech recognition. The method includes selecting a speaker independent model, and selecting a quantity of speaker dependent models, the quantity of speaker dependent models being based on available computing resources, the selected models including the speaker independent model and the quantity of speaker dependent models. The method also includes recognizing an utterance using each of the selected models in parallel, and selecting a dominant speech model from the selected models based on recognition accuracy using the group of selected models. The system includes a processor and modules configured to control the processor to perform the method. The computer-readable storage medium includes instructions for causing a computing device to perform the steps of the method.

System and method for personalization of acoustic models for automatic speech recognition

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, relating to generating log-linear models. In some implementations, n-gram parameter values derived from an n-gram language model are obtained. N-gram features for a log-linear language model are determined based on the n-grams corresponding to the obtained n-gram parameter values. A weight for each of the determined n-gram features is determined, where the weight is determined based on (i) an n-gram parameter value that is derived from the n-gram language model and that corresponds to a particular n-gram, and (ii) an n-gram parameter value that is derived from the n-gram language model and that corresponds to an n-gram that is a sub-sequence within the particular n-gram. A log-linear language model having the determined n-gram features is generated, where the determined n-gram features in the log-linear language model have weights that are initialized based on the determined weights.

Speech recognition using log-linear model

Disclosed herein are systems, methods, and computer-readable storage media for a speech recognition application for directory assistance that is based on a user's spoken search query. The spoken search query is received by a portable device and portable device then determines its present location. Upon determining the location of the portable device, that information is incorporated into a local language model that is used to process the search query. Finally, the portable device outputs the results of the search query based on the local language model.

System and method for combining geographic metadata in automatic speech recognition language and acoustic models

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for assigning saliency weights to words of an ASR model. The saliency values assigned to words within an ASR model are based on human perception judgments of previous transcripts. These saliency values are applied as weights to modify an ASR model such that the results of the weighted ASR model in converting a spoken document to a transcript provide a more accurate and useful transcription to the user.

System and method for optimizing speech recognition and natural language parameters with user feedback

Systems and methods for addressing missing features in models are provided. In some implementations, a model configured to indicate likelihoods of different outcomes is accessed. The model includes a respective score for each of a plurality of features, and each feature corresponds to an outcome in an associated context. It is determined that the model does not include a score for a feature corresponding to a potential outcome in a particular context. A score is determined for the potential outcome in the particular context based on the scores for one or more features in the model that correspond to different outcomes in the particular context. The model and the score are used to determine a likelihood of occurrence of the potential outcome.

Addressing missing features in models

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating an acoustic model for use in speech recognition. A system configured to practice the method first receives training data and identifies non-contextual lexical-level features in the training data. Then the system infers sentence-level features from the training data and generates a set of decision trees by node-splitting based on the non-contextual lexical-level features and the sentence-level features. The system decorrelates training vectors, based on the training data, for each decision tree in the set of decision trees to approximate full-covariance Gaussian models, and then can train an acoustic model for use in speech recognition based on the training data, the set of decision trees, and the training vectors.

System and method for speech recognition modeling for mobile voice search

Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for handling expected repeat speech queries or other inputs. The method causes a computing device to detect a misrecognized speech query from a user, determine a tendency of the user to repeat speech queries based on previous user interactions, and adapt a speech recognition model based on the determined tendency before an expected repeat speech query. The method can further include recognizing the expected repeat speech query from the user based on the adapted speech recognition model. Adapting the speech recognition model can include modifying an acoustic model, a language model, and a semantic model. Adapting the speech recognition model can also include preparing a personalized search speech recognition model for the expected repeat query based on usage history and entries in a recognition lattice. The method can include retaining unmodified speech recognition models with adapted speech recognition models.

Growing community of inventors

Philadelphia, PA, United States of America

Diamantino Antonio Caseiro