Patents by Inventor Maria Carolina Parada San Martin

Maria Carolina Parada San Martin 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: 10714096
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining hotword suitability. In one aspect, a method includes receiving speech data that encodes a candidate hotword spoken by a user, evaluating the speech data or a transcription of the candidate hotword, using one or more predetermined criteria, generating a hotword suitability score for the candidate hotword based on evaluating the speech data or a transcription of the candidate hotword, using one or more predetermined criteria, and providing a representation of the hotword suitability score for display to the user.
    Type: Grant
    Filed: May 16, 2018
    Date of Patent: July 14, 2020
    Assignee: Google LLC
    Inventors: Andrew Rubin, Johan Schalkwyk, Maria Carolina Parada San Martin
  • Publication number: 20200168242
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting an end of a query are disclosed. In one aspect, a method includes the actions of receiving audio data that corresponds to an utterance spoken by a user. The actions further include applying, to the audio data, an end of query model. The actions further include determining the confidence score that reflects a likelihood that the utterance is a complete utterance. The actions further include comparing the confidence score that reflects the likelihood that the utterance is a complete utterance to a confidence score threshold. The actions further include determining whether the utterance is likely complete or likely incomplete. The actions further include providing, for output, an instruction to (i) maintain a microphone that is receiving the utterance in an active state or (ii) deactivate the microphone that is receiving the utterance.
    Type: Application
    Filed: January 31, 2020
    Publication date: May 28, 2020
    Applicant: Google LLC
    Inventors: Gabor Simko, Maria Carolina Parada San Martin, Sean Matthew Shannon
  • Publication number: 20200117996
    Abstract: A method for training an endpointer model includes short-form speech utterances and long-form speech utterances. The method also includes providing a short-form speech utterance as input to a shared neural network, the shared neural network configured to learn shared hidden representations suitable for both voice activity detection (VAD) and end-of-query (EOQ) detection. The method also includes generating, using a VAD classifier, a sequence of predicted VAD labels and determining a VAD loss by comparing the sequence of predicted VAD labels to a corresponding sequence of reference VAD labels. The method also includes, generating, using an EOQ classifier, a sequence of predicted EOQ labels and determining an EOQ loss by comparing the sequence of predicted EOQ labels to a corresponding sequence of reference EOQ labels. The method also includes training, using a cross-entropy criterion, the endpointer model based on the VAD loss and the EOQ loss.
    Type: Application
    Filed: December 11, 2019
    Publication date: April 16, 2020
    Applicant: Google LLC
    Inventors: Shuo-yiin Chang, Bo Li, Gabor Simko, Maria Carolina Parada San Martin, Sean Matthew Shannon
  • Patent number: 10593352
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting an end of a query are disclosed. In one aspect, a method includes the actions of receiving audio data that corresponds to an utterance spoken by a user. The actions further include applying, to the audio data, an end of query model. The actions further include determining the confidence score that reflects a likelihood that the utterance is a complete utterance. The actions further include comparing the confidence score that reflects the likelihood that the utterance is a complete utterance to a confidence score threshold. The actions further include determining whether the utterance is likely complete or likely incomplete. The actions further include providing, for output, an instruction to (i) maintain a microphone that is receiving the utterance in an active state or (ii) deactivate the microphone that is receiving the utterance.
    Type: Grant
    Filed: June 6, 2018
    Date of Patent: March 17, 2020
    Assignee: Google LLC
    Inventors: Gabor Simko, Maria Carolina Parada San Martin, Sean Matthew Shannon
  • Publication number: 20200051551
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for keyword spotting. One of the methods includes training, by a keyword detection system, a convolutional neural network for keyword detection by providing a two-dimensional set of input values to the convolutional neural network, the input values including a first dimension in time and a second dimension in frequency, and performing convolutional multiplication on the two-dimensional set of input values for a filter using a frequency stride greater than one to generate a feature map.
    Type: Application
    Filed: October 16, 2019
    Publication date: February 13, 2020
    Applicant: Google LLC
    Inventors: Tara N. Sainath, Maria Carolina Parada San Martin
  • Publication number: 20190304459
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for classification using neural networks. One method includes receiving audio data corresponding to an utterance. Obtaining a transcription of the utterance. Generating a representation of the audio data. Generating a representation of the transcription of the utterance. Providing (i) the representation of the audio data and (ii) the representation of the transcription of the utterance to a classifier that, based on a given representation of the audio data and a given representation of the transcription of the utterance, is trained to output an indication of whether the utterance associated with the given representation is likely directed to an automated assistance or is likely not directed to an automated assistant.
    Type: Application
    Filed: May 2, 2019
    Publication date: October 3, 2019
    Inventors: Nathan David Howard, Gabor Simko, Maria Carolina Parada San Martin, Ramkarthik Kalyanasundaram, Guru Prakash Arumugam, Srinivas Vasudevan
  • Patent number: 10311872
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for classification using neural networks. One method includes receiving audio data corresponding to an utterance. Obtaining a transcription of the utterance. Generating a representation of the audio data. Generating a representation of the transcription of the utterance. Providing (i) the representation of the audio data and (ii) the representation of the transcription of the utterance to a classifier that, based on a given representation of the audio data and a given representation of the transcription of the utterance, is trained to output an indication of whether the utterance associated with the given representation is likely directed to an automated assistance or is likely not directed to an automated assistant.
    Type: Grant
    Filed: July 25, 2017
    Date of Patent: June 4, 2019
    Assignee: Google LLC
    Inventors: Nathan David Howard, Gabor Simko, Maria Carolina Parada San Martin, Ramkarthik Kalyanasundaram, Guru Prakash Arumugam, Srinivas Vasudevan
  • Patent number: 10229700
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting voice activity. In one aspect, a method include actions of receiving, by a neural network included in an automated voice activity detection system, a raw audio waveform, processing, by the neural network, the raw audio waveform to determine whether the audio waveform includes speech, and provide, by the neural network, a classification of the raw audio waveform indicating whether the raw audio waveform includes speech.
    Type: Grant
    Filed: January 4, 2016
    Date of Patent: March 12, 2019
    Assignee: Google LLC
    Inventors: Tara N. Sainath, Gabor Simko, Maria Carolina Parada San Martin, Ruben Zazo Candil
  • Publication number: 20190035390
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for classification using neural networks. One method includes receiving audio data corresponding to an utterance. Obtaining a transcription of the utterance. Generating a representation of the audio data. Generating a representation of the transcription of the utterance. Providing (i) the representation of the audio data and (ii) the representation of the transcription of the utterance to a classifier that, based on a given representation of the audio data and a given representation of the transcription of the utterance, is trained to output an indication of whether the utterance associated with the given representation is likely directed to an automated assistance or is likely not directed to an automated assistant.
    Type: Application
    Filed: July 25, 2017
    Publication date: January 31, 2019
    Inventors: Nathan David Howard, Gabor Simko, Maria Carolina Parada San Martin, Ramkarthik Kalyanasundaram, Guru Prakash Arumugam, Srinivas Vasudevan
  • Publication number: 20180350395
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting an end of a query are disclosed. In one aspect, a method includes the actions of receiving audio data that corresponds to an utterance spoken by a user. The actions further include applying, to the audio data, an end of query model. The actions further include determining the confidence score that reflects a likelihood that the utterance is a complete utterance. The actions further include comparing the confidence score that reflects the likelihood that the utterance is a complete utterance to a confidence score threshold. The actions further include determining whether the utterance is likely complete or likely incomplete. The actions further include providing, for output, an instruction to (i) maintain a microphone that is receiving the utterance in an active state or (ii) deactivate the microphone that is receiving the utterance.
    Type: Application
    Filed: June 6, 2018
    Publication date: December 6, 2018
    Inventors: Gabor Simko, Maria Carolina Parada San Martin, Sean Matthew Shannon
  • Publication number: 20180336906
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining hotword suitability. In one aspect, a method includes receiving speech data that encodes a candidate hotword spoken by a user, evaluating the speech data or a transcription of the candidate hotword, using one or more predetermined criteria, generating a hotword suitability score for the candidate hotword based on evaluating the speech data or a transcription of the candidate hotword, using one or more predetermined criteria, and providing a representation of the hotword suitability score for display to the user.
    Type: Application
    Filed: May 16, 2018
    Publication date: November 22, 2018
    Inventors: Andrew Rubin, Johan Schalkwyk, Maria Carolina Parada San Martin
  • Patent number: 10002613
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining hotword suitability. In one aspect, a method includes receiving speech data that encodes a candidate hotword spoken by a user, evaluating the speech data or a transcription of the candidate hotword, using one or more predetermined criteria, generating a hotword suitability score for the candidate hotword based on evaluating the speech data or a transcription of the candidate hotword, using one or more predetermined criteria, and providing a representation of the hotword suitability score for display to the user.
    Type: Grant
    Filed: January 20, 2016
    Date of Patent: June 19, 2018
    Assignee: Google LLC
    Inventors: Andrew E. Rubin, Johan Schalkwyk, Maria Carolina Parada San Martin
  • Patent number: 9754584
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for recognizing keywords using a long short term memory neural network. One of the methods includes receiving, by a device for each of multiple variable length enrollment audio signals, a respective plurality of enrollment feature vectors that represent features of the respective variable length enrollment audio signal, processing each of the plurality of enrollment feature vectors using a long short term memory (LSTM) neural network to generate a respective enrollment LSTM output vector for each enrollment feature vector, and generating, for the respective variable length enrollment audio signal, a template fixed length representation for use in determining whether another audio signal encodes another spoken utterance of the enrollment phrase by combining at most a quantity k of the enrollment LSTM output vectors for the enrollment audio signal.
    Type: Grant
    Filed: November 8, 2016
    Date of Patent: September 5, 2017
    Assignee: Google Inc.
    Inventors: Maria Carolina Parada San Martin, Tara N. Sainath, Guoguo Chen
  • Patent number: 9715660
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a deep neural network. One of the methods includes training a deep neural network with a first training set by adjusting values for each of a plurality of weights included in the neural network, and training the deep neural network to determine a probability that data received by the deep neural network has features similar to key features of one or more keywords or key phrases, the training comprising providing the deep neural network with a second training set and adjusting the values for a first subset of the plurality of weights, wherein the second training set includes data representing the key features of the one or more keywords or key phrases.
    Type: Grant
    Filed: March 31, 2014
    Date of Patent: July 25, 2017
    Assignee: Google Inc.
    Inventors: Maria Carolina Parada San Martin, Guoguo Chen, Georg Heigold
  • Patent number: 9646634
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a deep neural network. One of the methods for training a deep neural network that includes a low rank hidden input layer and an adjoining hidden layer, the low rank hidden input layer including a first matrix A and a second matrix B with dimensions i×m and m×o, respectively, to identify a keyword includes receiving a feature vector including i values that represent features of an audio signal encoding an utterance, determining, using the low rank hidden input layer, an output vector including o values using the feature vector, determining, using the adjoining hidden layer, another vector using the output vector, determining a confidence score that indicates whether the utterance includes the keyword using the other vector, and adjusting weights for the low rank hidden input layer using the confidence score.
    Type: Grant
    Filed: February 9, 2015
    Date of Patent: May 9, 2017
    Assignee: Google Inc.
    Inventors: Tara N. Sainath, Maria Carolina Parada San Martin
  • Publication number: 20170092297
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting voice activity. In one aspect, a method include actions of receiving, by a neural network included in an automated voice activity detection system, a raw audio waveform, processing, by the neural network, the raw audio waveform to determine whether the audio waveform includes speech, and provide, by the neural network, a classification of the raw audio waveform indicating whether the raw audio waveform includes speech.
    Type: Application
    Filed: January 4, 2016
    Publication date: March 30, 2017
    Inventors: Tara N. Sainath, Gabor Simko, Maria Carolina Parada San Martin
  • Publication number: 20170076717
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for recognizing keywords using a long short term memory neural network. One of the methods includes receiving, by a device for each of multiple variable length enrollment audio signals, a respective plurality of enrollment feature vectors that represent features of the respective variable length enrollment audio signal, processing each of the plurality of enrollment feature vectors using a long short term memory (LSTM) neural network to generate a respective enrollment LSTM output vector for each enrollment feature vector, and generating, for the respective variable length enrollment audio signal, a template fixed length representation for use in determining whether another audio signal encodes another spoken utterance of the enrollment phrase by combining at most a quantity k of the enrollment LSTM output vectors for the enrollment audio signal.
    Type: Application
    Filed: November 8, 2016
    Publication date: March 16, 2017
    Inventors: Maria Carolina Parada San Martin, Tara N. Sainath, Guoguo Chen
  • Patent number: 9536528
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining hotword suitability. In one aspect, a method includes receiving speech data that encodes a candidate hotword spoken by a user, evaluating the speech data or a transcription of the candidate hotword, using one or more predetermined criteria, generating a hotword suitability score for the candidate hotword based on evaluating the speech data or a transcription of the candidate hotword, using one or more predetermined criteria, and providing a representation of the hotword suitability score for display to the user.
    Type: Grant
    Filed: August 6, 2012
    Date of Patent: January 3, 2017
    Assignee: Google Inc.
    Inventors: Andrew E. Rubin, Johan Schalkwyk, Maria Carolina Parada San Martin
  • Patent number: 9508340
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for recognizing keywords using a long short term memory neural network. One of the methods includes receiving, by a device for each of multiple variable length enrollment audio signals, a respective plurality of enrollment feature vectors that represent features of the respective variable length enrollment audio signal, processing each of the plurality of enrollment feature vectors using a long short term memory (LSTM) neural network to generate a respective enrollment LSTM output vector for each enrollment feature vector, and generating, for the respective variable length enrollment audio signal, a template fixed length representation for use in determining whether another audio signal encodes another spoken utterance of the enrollment phrase by combining at most a quantity k of the enrollment LSTM output vectors for the enrollment audio signal.
    Type: Grant
    Filed: December 22, 2014
    Date of Patent: November 29, 2016
    Assignee: Google Inc.
    Inventors: Maria Carolina Parada San Martin, Tara N. Sainath, Guoguo Chen
  • Publication number: 20160293167
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing speaker verification. In one aspect, a method includes accessing a neural network having an input layer that provides inputs to a first hidden layer whose nodes are respectively connected to only a proper subset of the inputs from the input layer. Speech data that corresponds to a particular utterance may be provided as input to the input layer of the neural network. A representation of activations that occur in response to the speech data at a particular layer of the neural network that was configured as a hidden layer during training of the neural network may be generated. A determination of whether the particular utterance was likely spoken by a particular speaker may be made based at least on the generated representation. An indication of whether the particular utterance was likely spoken by the particular speaker may be provided.
    Type: Application
    Filed: June 10, 2016
    Publication date: October 6, 2016
    Inventors: Yu-hsin Joyce Chen, Ignacio Lopez Moreno, Tara N. Sainath, Maria Carolina Parada San Martin