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).

  • Patent number: 11557277
    Abstract: 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: Grant
    Filed: December 15, 2021
    Date of Patent: January 17, 2023
    Assignee: Google LLC
    Inventors: Georg Heigold, Erik McDermott, Vincent O. VanHoucke, Andrew W. Senior, Michiel A. U. Bacchiani
  • Publication number: 20220262350
    Abstract: 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: Application
    Filed: May 3, 2022
    Publication date: August 18, 2022
    Applicant: Google LLC
    Inventors: Kanury Kanishka Rao, Andrew W. Senior, Hasim Sak
  • Patent number: 11341958
    Abstract: 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: Grant
    Filed: September 16, 2020
    Date of Patent: May 24, 2022
    Assignee: Google LLC
    Inventors: Kanury Kanishka Rao, Andrew W. Senior, Hasim Sak
  • Publication number: 20220108686
    Abstract: 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: Application
    Filed: December 15, 2021
    Publication date: April 7, 2022
    Applicant: Google LLC
    Inventors: Georg Heigold, Erik McDermott, Vincent O. VanHoucke, Andrew W. Senior, Michiel A.U. Bacchiani
  • Patent number: 11227582
    Abstract: 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: Grant
    Filed: January 6, 2021
    Date of Patent: January 18, 2022
    Assignee: Google LLC
    Inventors: Georg Heigold, Erik Mcdermott, Vincent O. Vanhoucke, Andrew W. Senior, Michiel A. U. Bacchiani
  • Publication number: 20210407625
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction. In one aspect, a method comprises generating a distance map for a given protein, wherein the given protein is defined by a sequence of amino acid residues arranged in a structure, wherein the distance map characterizes estimated distances between the amino acid residues in the structure, comprising: generating a plurality of distance map crops, wherein each distance map crop characterizes estimated distances between (i) amino acid residues in each of one or more respective first positions in the sequence and (ii) amino acid residues in each of one or more respective second positions in the sequence in the structure of the protein, wherein the first positions are a proper subset of the sequence; and generating the distance map for the given protein using the plurality of distance map crops.
    Type: Application
    Filed: September 16, 2019
    Publication date: December 30, 2021
    Inventors: Andrew W. Senior, James Kirkpatrick, Laurent Sifre, Richard Andrew Evans, Hugo Penedones, Chongli Qin, Ruoxi Sun, Karen Simonyan, John Jumper
  • Publication number: 20210398606
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a predicted structure of a protein that is specified by an amino acid sequence. In one aspect, a method comprises: obtaining an initial embedding and initial values of structure parameters for each amino acid in the amino acid sequence, wherein the structure parameters for each amino acid comprise location parameters that specify a predicted three-dimensional spatial location of the amino acid in the structure of the protein; and processing a network input comprising the initial embedding and the initial values of the structure parameters for each amino acid in the amino acid sequence using a folding neural network to generate a network output comprising final values of the structure parameters for each amino acid in the amino acid sequence.
    Type: Application
    Filed: December 2, 2019
    Publication date: December 23, 2021
    Inventors: John Jumper, Andrew W. Senior, Richard Andrew Evans, Stephan Gouws, Alexander Bridgland
  • Publication number: 20210313008
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction and protein domain segmentation. In one aspect, a method comprises generating a plurality of predicted structures of a protein, wherein generating a predicted structure of the protein comprises: updating initial values of a plurality of structure parameters of the protein, comprising, at each of a plurality of update iterations: determining a gradient of a quality score for the current values of the structure parameters with respect to the current values of the structure parameters; and updating the current values of the structure parameters using the gradient.
    Type: Application
    Filed: September 16, 2019
    Publication date: October 7, 2021
    Inventors: Andrew W. Senior, James Kirkpatrick, Laurent Sifre, Richard Andrew Evans, Hugo Penedones, Chongli Qin, Ruoxi Sun, Karen Simonyan, John Jumper
  • Publication number: 20210304847
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction. In one aspect, a method comprises, at each of one or more iterations: determining an alternative predicted structure of a given protein defined by alternative values of structure parameters; processing, using a geometry neural network, a network input comprising: (i) a representation of a sequence of amino acid residues in the given protein, and (ii) the alternative values of the structure parameters, to generate an output characterizing an alternative geometry score that is an estimate of a similarity measure between the alternative predicted structure and the actual structure of the given protein.
    Type: Application
    Filed: September 16, 2019
    Publication date: September 30, 2021
    Inventors: Andrew W. Senior, James Kirkpatrick, Laurent Sifre, Richard Andrew Evans, Hugo Penedones, Chongli Qin, Ruoxi Sun, Karen Simonyan, John Jumper
  • Publication number: 20210183376
    Abstract: 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: Application
    Filed: January 21, 2021
    Publication date: June 17, 2021
    Applicant: Google LLC
    Inventors: Andrew W. Senior, Ignacio L. Moreno
  • Publication number: 20210166779
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a predicted structure of a protein that is specified by an amino acid sequence. In one aspect, a method comprises: obtaining a multiple sequence alignment for the protein; determining, from the multiple sequence alignment and for each pair of amino acids in the amino acid sequence of the protein, a respective initial embedding of the pair of amino acids; processing the initial embeddings of the pairs of amino acids using a pair embedding neural network comprising a plurality of self-attention neural network layers to generate a final embedding of each pair of amino acids; and determining the predicted structure of the protein based on the final embedding of each pair of amino acids.
    Type: Application
    Filed: December 1, 2020
    Publication date: June 3, 2021
    Inventors: John Jumper, Andrew W. Senior, Richard Andrew Evans, Russell James Bates, Mikhail Figurnov, Alexander Pritzel, Timothy Frederick Goldie Green
  • Publication number: 20210134275
    Abstract: 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: Application
    Filed: January 8, 2021
    Publication date: May 6, 2021
    Applicant: Google LLC
    Inventors: Hasim Sak, Andrew W. Senior
  • Publication number: 20210125601
    Abstract: 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: Application
    Filed: January 6, 2021
    Publication date: April 29, 2021
    Applicant: Google LLC
    Inventors: Georg Heigold, Erik Mcdermott, Vincent O. Vanhoucke, Andrew W. Senior, Michiel A.U. Bacchiani
  • Patent number: 10930271
    Abstract: 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: Grant
    Filed: September 17, 2019
    Date of Patent: February 23, 2021
    Inventors: Andrew W. Senior, Ignacio Lopez Moreno
  • Patent number: 10930270
    Abstract: 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: Grant
    Filed: August 15, 2019
    Date of Patent: February 23, 2021
    Assignee: Google LLC
    Inventors: Tara N. Sainath, Ron J. Weiss, Andrew W. Senior, Kevin William Wilson
  • Patent number: 10923112
    Abstract: 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: Grant
    Filed: December 5, 2019
    Date of Patent: February 16, 2021
    Assignee: Google LLC
    Inventors: Hasim Sak, Andrew W. Senior
  • Patent number: 10916238
    Abstract: 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: Grant
    Filed: April 30, 2020
    Date of Patent: February 9, 2021
    Assignee: Google LLC
    Inventors: Georg Heigold, Erik Mcdermott, Vincent O. Vanhoucke, Andrew W. Senior, Michiel A. U. Bacchiani
  • Publication number: 20210005184
    Abstract: 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: Application
    Filed: September 16, 2020
    Publication date: January 7, 2021
    Applicant: Google LLC
    Inventors: Kanury Kanishka Rao, Andrew W. Senior, Hasim Sak
  • Publication number: 20200335093
    Abstract: 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: Application
    Filed: July 1, 2020
    Publication date: October 22, 2020
    Applicant: Google LLC
    Inventors: Andrew W Senior, Hasim Sak, Kanury Kanishka Rao
  • Patent number: 10803855
    Abstract: 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: Grant
    Filed: January 25, 2019
    Date of Patent: October 13, 2020
    Assignee: Google LLC
    Inventors: Kanury Kanishka Rao, Andrew W. Senior, Hasim Sak