Patents by Inventor Andrew W. Senior
Andrew W. Senior has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20210125601Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.Type: ApplicationFiled: January 6, 2021Publication date: April 29, 2021Applicant: Google LLCInventors: Georg Heigold, Erik Mcdermott, Vincent O. Vanhoucke, Andrew W. Senior, Michiel A.U. Bacchiani
-
Patent number: 10930270Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing audio waveforms. In some implementations, a time-frequency feature representation is generated based on audio data. The time-frequency feature representation is input to an acoustic model comprising a trained artificial neural network. The trained artificial neural network comprising a frequency convolution layer, a memory layer, and one or more hidden layers. An output that is based on output of the trained artificial neural network is received. A transcription is provided, where the transcription is determined based on the output of the acoustic model.Type: GrantFiled: August 15, 2019Date of Patent: February 23, 2021Assignee: Google LLCInventors: Tara N. Sainath, Ron J. Weiss, Andrew W. Senior, Kevin William Wilson
-
Patent number: 10930271Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using neural networks. A feature vector that models audio characteristics of a portion of an utterance is received. Data indicative of latent variables of multivariate factor analysis is received. The feature vector and the data indicative of the latent variables is provided as input to a neural network. A candidate transcription for the utterance is determined based on at least an output of the neural network.Type: GrantFiled: September 17, 2019Date of Patent: February 23, 2021Inventors: Andrew W. Senior, Ignacio Lopez Moreno
-
Patent number: 10923112Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating representation of acoustic sequences. One of the methods includes: receiving an acoustic sequence, the acoustic sequence comprising a respective acoustic feature representation at each of a plurality of time steps; processing the acoustic feature representation at an initial time step using an acoustic modeling neural network; for each subsequent time step of the plurality of time steps: receiving an output generated by the acoustic modeling neural network for a preceding time step, generating a modified input from the output generated by the acoustic modeling neural network for the preceding time step and the acoustic representation for the time step, and processing the modified input using the acoustic modeling neural network to generate an output for the time step; and generating a phoneme representation for the utterance from the outputs for each of the time steps.Type: GrantFiled: December 5, 2019Date of Patent: February 16, 2021Assignee: Google LLCInventors: Hasim Sak, Andrew W. Senior
-
Patent number: 10916238Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.Type: GrantFiled: April 30, 2020Date of Patent: February 9, 2021Assignee: Google LLCInventors: Georg Heigold, Erik Mcdermott, Vincent O. Vanhoucke, Andrew W. Senior, Michiel A. U. Bacchiani
-
Publication number: 20210005184Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training acoustic models and using the trained acoustic models. A connectionist temporal classification (CTC) acoustic model is accessed, the CTC acoustic model having been trained using a context-dependent state inventory generated from approximate phonetic alignments determined by another CTC acoustic model trained without fixed alignment targets. Audio data for a portion of an utterance is received. Input data corresponding to the received audio data is provided to the accessed CTC acoustic model. Data indicating a transcription for the utterance is generated based on output that the accessed CTC acoustic model produced in response to the input data. The data indicating the transcription is provided as output of an automated speech recognition service.Type: ApplicationFiled: September 16, 2020Publication date: January 7, 2021Applicant: Google LLCInventors: Kanury Kanishka Rao, Andrew W. Senior, Hasim Sak
-
Publication number: 20200335093Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for acoustic modeling of audio data. One method includes receiving audio data representing a portion of an utterance, providing the audio data to a trained recurrent neural network that has been trained to indicate the occurrence of a phone at any of multiple time frames within a maximum delay of receiving audio data corresponding to the phone, receiving, within the predetermined maximum delay of providing the audio data to the trained recurrent neural network, output of the trained neural network indicating a phone corresponding to the provided audio data using output of the trained neural network to determine a transcription for the utterance, and providing the transcription for the utterance.Type: ApplicationFiled: July 1, 2020Publication date: October 22, 2020Applicant: Google LLCInventors: Andrew W Senior, Hasim Sak, Kanury Kanishka Rao
-
Patent number: 10803855Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training acoustic models and using the trained acoustic models. A connectionist temporal classification (CTC) acoustic model is accessed, the CTC acoustic model having been trained using a context-dependent state inventory generated from approximate phonetic alignments determined by another CTC acoustic model trained without fixed alignment targets. Audio data for a portion of an utterance is received. Input data corresponding to the received audio data is provided to the accessed CTC acoustic model. Data indicating a transcription for the utterance is generated based on output that the accessed CTC acoustic model produced in response to the input data. The data indicating the transcription is provided as output of an automated speech recognition service.Type: GrantFiled: January 25, 2019Date of Patent: October 13, 2020Assignee: Google LLCInventors: Kanury Kanishka Rao, Andrew W. Senior, Hasim Sak
-
Patent number: 10783900Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying the language of a spoken utterance. One of the methods includes receiving input features of an utterance; and processing the input features using an acoustic model that comprises one or more convolutional neural network (CNN) layers, one or more long short-term memory network (LSTM) layers, and one or more fully connected neural network layers to generate a transcription for the utterance.Type: GrantFiled: September 8, 2015Date of Patent: September 22, 2020Assignee: Google LLCInventors: Tara N. Sainath, Andrew W. Senior, Oriol Vinyals, Hasim Sak
-
Publication number: 20200258500Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.Type: ApplicationFiled: April 30, 2020Publication date: August 13, 2020Applicant: Google LLCInventors: Georg Heigold, Erik McDermott, Vincent O. Vanhoucke, Andrew W. Senior, Michiel A.U. Bacchiani
-
Patent number: 10733979Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for acoustic modeling of audio data. One method includes receiving audio data representing a portion of an utterance, providing the audio data to a trained recurrent neural network that has been trained to indicate the occurrence of a phone at any of multiple time frames within a maximum delay of receiving audio data corresponding to the phone, receiving, within the predetermined maximum delay of providing the audio data to the trained recurrent neural network, output of the trained neural network indicating a phone corresponding to the provided audio data using output of the trained neural network to determine a transcription for the utterance, and providing the transcription for the utterance.Type: GrantFiled: October 9, 2015Date of Patent: August 4, 2020Assignee: Google LLCInventors: Andrew W. Senior, Hasim Sak, Kanury Kanishka Rao
-
Patent number: 10720176Abstract: A computer-implemented method of multisensory speech detection is disclosed. The method comprises determining an orientation of a mobile device and determining an operating mode of the mobile device based on the orientation of the mobile device. The method further includes identifying speech detection parameters that specify when speech detection begins or ends based on the determined operating mode and detecting speech from a user of the mobile device based on the speech detection parameters.Type: GrantFiled: August 22, 2018Date of Patent: July 21, 2020Assignee: Google LLCInventors: Dave Burke, Michael J. Lebeau, Konrad Gianno, Trausti T. Kristjansson, John Nicholas Jitkoff, Andrew W. Senior
-
Patent number: 10714120Abstract: A computer-implemented method of multisensory speech detection is disclosed. The method comprises determining an orientation of a mobile device and determining an operating mode of the mobile device based on the orientation of the mobile device. The method further includes identifying speech detection parameters that specify when speech detection begins or ends based on the determined operating mode and detecting speech from a user of the mobile device based on the speech detection parameters.Type: GrantFiled: June 25, 2018Date of Patent: July 14, 2020Assignee: Google LLCInventors: Dave Burke, Michael J. Lebeau, Konrad Gianno, Trausti T. Kristjansson, John Nicholas Jitkoff, Andrew W. Senior
-
Patent number: 10672384Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.Type: GrantFiled: September 17, 2019Date of Patent: June 2, 2020Assignee: Google LLCInventors: Georg Heigold, Erik McDermott, Vincent O. Vanhoucke, Andrew W. Senior, Michiel A. U. Bacchiani
-
Publication number: 20200135227Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying the language of a spoken utterance. One of the methods includes receiving input features of an utterance; and processing the input features using an acoustic model that comprises one or more convolutional neural network (CNN) layers, one or more long short-term memory network (LSTM) layers, and one or more fully connected neural network layers to generate a transcription for the utterance.Type: ApplicationFiled: December 31, 2019Publication date: April 30, 2020Inventors: Tara N. Sainath, Andrew W. Senior, Oriol Vinyals, Hasim Sak
-
Publication number: 20200118549Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.Type: ApplicationFiled: September 17, 2019Publication date: April 16, 2020Inventors: Georg Heigold, Erik McDermott, Vincent O. Vanhoucke, Andrew W. Senior, Michiel A.U. Bacchiani
-
Publication number: 20200118552Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating representation of acoustic sequences. One of the methods includes: receiving an acoustic sequence, the acoustic sequence comprising a respective acoustic feature representation at each of a plurality of time steps; processing the acoustic feature representation at an initial time step using an acoustic modeling neural network; for each subsequent time step of the plurality of time steps: receiving an output generated by the acoustic modeling neural network for a preceding time step, generating a modified input from the output generated by the acoustic modeling neural network for the preceding time step and the acoustic representation for the time step, and processing the modified input using the acoustic modeling neural network to generate an output for the time step; and generating a phoneme representation for the utterance from the outputs for each of the time steps.Type: ApplicationFiled: December 5, 2019Publication date: April 16, 2020Applicant: Google LLCInventors: Hasim Sak, Andrew W. Senior
-
Publication number: 20200111481Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using neural networks. A feature vector that models audio characteristics of a portion of an utterance is received. Data indicative of latent variables of multivariate factor analysis is received. The feature vector and the data indicative of the latent variables is provided as input to a neural network. A candidate transcription for the utterance is determined based on at least an output of the neural network.Type: ApplicationFiled: September 17, 2019Publication date: April 9, 2020Inventors: Andrew W. Senior, Ignacio Lopez Moreno
-
Patent number: 10535338Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating representation of acoustic sequences. One of the methods includes: receiving an acoustic sequence, the acoustic sequence comprising a respective acoustic feature representation at each of a plurality of time steps; processing the acoustic feature representation at an initial time step using an acoustic modeling neural network; for each subsequent time step of the plurality of time steps: receiving an output generated by the acoustic modeling neural network for a preceding time step, generating a modified input from the output generated by the acoustic modeling neural network for the preceding time step and the acoustic representation for the time step, and processing the modified input using the acoustic modeling neural network to generate an output for the time step; and generating a phoneme representation for the utterance from the outputs for each of the time steps.Type: GrantFiled: November 2, 2018Date of Patent: January 14, 2020Assignee: Google LLCInventors: Hasim Sak, Andrew W. Senior
-
Publication number: 20190378498Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing audio waveforms. In some implementations, a time-frequency feature representation is generated based on audio data. The time-frequency feature representation is input to an acoustic model comprising a trained artificial neural network. The trained artificial neural network comprising a frequency convolution layer, a memory layer, and one or more hidden layers. An output that is based on output of the trained artificial neural network is received. A transcription is provided, where the transcription is determined based on the output of the acoustic model.Type: ApplicationFiled: August 15, 2019Publication date: December 12, 2019Inventors: Tara N. Sainath, Ron J. Weiss, Andrew W. Senior, Kevin William Wilson