Patents by Inventor Andrew M. Rosenberg

Andrew M. Rosenberg 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: 11913143
    Abstract: Interlacing equipment may be used to form fabric and to create a gap in the fabric. The fabric may include one or more conductive strands. An insertion tool may be used to align an electrical component with the conductive strands during interlacing operations. A soldering tool may be used to remove insulation from the conductive strands to expose conductive segments on the conductive strands. The soldering tool may be used to solder the conductive segments to the electrical component. The solder connections may be located in grooves in the electrical component. An encapsulation tool may dispense encapsulation material in the grooves to encapsulate the solder connections. After the electrical component is electrically connected to the conductive strands, the insertion tool may position and release the electrical component in the gap. A component retention tool may temporarily be used to retain the electrical component in the gap as interlacing operations continue.
    Type: Grant
    Filed: March 4, 2020
    Date of Patent: February 27, 2024
    Assignee: Apple Inc.
    Inventors: Kyle L Chatham, Kathryn P. Crews, Didio V. Gomes, Benjamin J. Grena, Storrs T. Hoen, Steven J. Keating, David M. Kindlon, Daniel A. Podhajny, Andrew L. Rosenberg, Daniel D. Sunshine, Lia M. Uesato, Joseph B. Walker, Felix Binder, Bertram Wendisch, Martin Latta, Ulrich Schläpfer, Franck Robin, Michael Baumann, Helen Wächter Fischer
  • Patent number: 11837216
    Abstract: A method for training a generative adversarial network (GAN)-based text-to-speech (TTS) model and a speech recognition model in unison includes obtaining a plurality of training text utterances. At each of a plurality of output steps for each training text utterance, the method also includes generating, for output by the GAN-Based TTS model, a synthetic speech representation of the corresponding training text utterance, and determining, using an adversarial discriminator of the GAN, an adversarial loss term indicative of an amount of acoustic noise disparity in one of the non-synthetic speech representations selected from the set of spoken training utterances relative to the corresponding synthetic speech representation of the corresponding training text utterance. The method also includes updating parameters of the GAN-based TTS model based on the adversarial loss term determined at each of the plurality of output steps for each training text utterance of the plurality of training text utterances.
    Type: Grant
    Filed: February 14, 2023
    Date of Patent: December 5, 2023
    Assignee: Google LLC
    Inventors: Zhehuai Chen, Andrew M. Rosenberg, Bhuvana Ramabhadran, Pedro J. Moreno Mengibar
  • Publication number: 20230317059
    Abstract: A method includes receiving training data that includes unspoken textual utterances, un-transcribed non-synthetic speech utterances, and transcribed non-synthetic speech utterances. Each unspoken textual utterance is not paired with any corresponding spoken utterance of non-synthetic speech. Each un-transcribed non-synthetic speech utterance not paired with a corresponding transcription. Each transcribed non-synthetic speech utterance paired with a corresponding transcription. The method also includes generating a corresponding alignment output for each unspoken textual utterance of the received training data using an alignment model. The method also includes pre-training an audio encoder on the alignment outputs generated for corresponding to the unspoken textual utterances, the un-transcribed non-synthetic speech utterances, and the transcribed non-synthetic speech utterances to teach the audio encoder to jointly learn shared speech and text representations.
    Type: Application
    Filed: February 13, 2023
    Publication date: October 5, 2023
    Applicant: Google LLC
    Inventors: Andrew M Rosenberg, Zhehuai Chen, Yu Zhang, Bhuvana Ramabhadran, Pedro J. Moreno Mengibar
  • Publication number: 20230298574
    Abstract: A method for speech conversion includes obtaining a speech conversion model configured to convert input utterances of human speech directly into corresponding output utterances of synthesized speech. The method further includes receiving a speech conversion request including input audio data corresponding to an utterance spoken by a target speaker associated with atypical speech and a speaker identifier uniquely identifying the target speaker. The method includes activating, using the speaker identifier, a particular sub-model for biasing the speech conversion model to recognize a type of the atypical speech associated with the target speaker identified by the speaker identifier.
    Type: Application
    Filed: March 15, 2023
    Publication date: September 21, 2023
    Applicant: Google LLC
    Inventors: Fadi Biadsy, Youzheng Chen, Xia Zhang, Oleg Rybakov, Andrew M. Rosenberg, Pedro J.Moreno Mengibar
  • Publication number: 20230298565
    Abstract: A method includes receiving a set of training utterances each including a non-synthetic speech representation of a corresponding utterance, and for each training utterance, generating a corresponding synthetic speech representation by using a voice conversion model. The non-synthetic speech representation and the synthetic speech representation form a corresponding training utterance pair. At each of a plurality of output steps for each training utterance pair, the method also includes generating, for output by a speech recognition model, a first probability distribution over possible non-synthetic speech recognition hypotheses for the non-synthetic speech representation and a second probability distribution over possible synthetic speech recognition hypotheses for the synthetic speech representation.
    Type: Application
    Filed: April 25, 2022
    Publication date: September 21, 2023
    Applicant: Google LLC
    Inventors: Andrew M. Rosenberg, Gary Wang, Bhuvana Ramabhadran, Fadi Biadsy
  • Publication number: 20230197057
    Abstract: A method for training a generative adversarial network (GAN)-based text-to-speech (TTS) model and a speech recognition model in unison includes obtaining a plurality of training text utterances. At each of a plurality of output steps for each training text utterance, the method also includes generating, for output by the GAN-Based TTS model, a synthetic speech representation of the corresponding training text utterance, and determining, using an adversarial discriminator of the GAN, an adversarial loss term indicative of an amount of acoustic noise disparity in one of the non-synthetic speech representations selected from the set of spoken training utterances relative to the corresponding synthetic speech representation of the corresponding training text utterance. The method also includes updating parameters of the GAN-based TTS model based on the adversarial loss term determined at each of the plurality of output steps for each training text utterance of the plurality of training text utterances.
    Type: Application
    Filed: February 14, 2023
    Publication date: June 22, 2023
    Applicant: Google LLC
    Inventors: Zhehuai Chen, Andrew M. Rosenberg, Bhuvana Ramabhadran, Pedro J. Moreno Mengibar
  • Publication number: 20230178068
    Abstract: A method includes receiving an input text sequence to be synthesized into speech in a first language and obtaining a speaker embedding, the speaker embedding specifying specific voice characteristics of a target speaker for synthesizing the input text sequence into speech that clones a voice of the target speaker. The target speaker includes a native speaker of a second language different than the first language. The method also includes generating, using a text-to-speech (TTS) model, an output audio feature representation of the input text by processing the input text sequence and the speaker embedding. The output audio feature representation includes the voice characteristics of the target speaker specified by the speaker embedding.
    Type: Application
    Filed: January 30, 2023
    Publication date: June 8, 2023
    Applicant: Google LLC
    Inventors: Yu Zhang, Ron J. Weiss, Byungha Chun, Yonghui Wu, Zhifeng Chen, Russell John Wyatt Skerry-Ryan, Ye Jia, Andrew M. Rosenberg, Bhuvana Ramabhadran
  • Patent number: 11605368
    Abstract: A method for training a generative adversarial network (GAN)-based text-to-speech (TTS) model and a speech recognition model in unison includes obtaining a plurality of training text utterances. At each of a plurality of output steps for each training text utterance, the method also includes generating, for output by the GAN-Based TTS model, a synthetic speech representation of the corresponding training text utterance, and determining, using an adversarial discriminator of the GAN, an adversarial loss term indicative of an amount of acoustic noise disparity in one of the non-synthetic speech representations selected from the set of spoken training utterances relative to the corresponding synthetic speech representation of the corresponding training text utterance. The method also includes updating parameters of the GAN-based TTS model based on the adversarial loss term determined at each of the plurality of output steps for each training text utterance of the plurality of training text utterances.
    Type: Grant
    Filed: November 11, 2021
    Date of Patent: March 14, 2023
    Assignee: Google LLC
    Inventors: Zhehuai Chen, Andrew M. Rosenberg, Bhuvana Ramabhadran, Pedro J. Moreno Mengibar
  • Patent number: 11580952
    Abstract: A method includes receiving an input text sequence to be synthesized into speech in a first language and obtaining a speaker embedding, the speaker embedding specifying specific voice characteristics of a target speaker for synthesizing the input text sequence into speech that clones a voice of the target speaker. The target speaker includes a native speaker of a second language different than the first language. The method also includes generating, using a text-to-speech (TTS) model, an output audio feature representation of the input text by processing the input text sequence and the speaker embedding. The output audio feature representation includes the voice characteristics of the target speaker specified by the speaker embedding.
    Type: Grant
    Filed: April 22, 2020
    Date of Patent: February 14, 2023
    Assignee: Google LLC
    Inventors: Yu Zhang, Ron J. Weiss, Byungha Chun, Yonghui Wu, Zhifeng Chen, Russell John Wyatt Skerry-Ryan, Ye Jia, Andrew M. Rosenberg, Bhuvana Ramabhadran
  • Publication number: 20230017892
    Abstract: A method includes receiving training data that includes unspoken text utterances and un-transcribed non-synthetic speech utterances. Each unspoken text utterance is not paired with any corresponding spoken utterance of non-synthetic speech. Each un-transcribed non-synthetic speech utterance is not paired with a corresponding transcription. The method also includes generating a corresponding synthetic speech representation for each unspoken textual utterance of the received training data using a text-to-speech model. The method also includes pre-training an audio encoder on the synthetic speech representations generated for the unspoken textual utterances and the un-transcribed non-synthetic speech utterances to teach the audio encoder to jointly learn shared speech and text representations.
    Type: Application
    Filed: June 21, 2022
    Publication date: January 19, 2023
    Applicant: Google LLC
    Inventors: Zhehuai Chen, Bhuvana Ramabhadran, Andrew M. Rosenberg, Yu Zhang, Pedro J. Moreno Mengibar
  • Publication number: 20220068255
    Abstract: A method for training a generative adversarial network (GAN)-based text-to-speech (TTS) model and a speech recognition model in unison includes obtaining a plurality of training text utterances. At each of a plurality of output steps for each training text utterance, the method also includes generating, for output by the GAN-Based TTS model, a synthetic speech representation of the corresponding training text utterance, and determining, using an adversarial discriminator of the GAN, an adversarial loss term indicative of an amount of acoustic noise disparity in one of the non-synthetic speech representations selected from the set of spoken training utterances relative to the corresponding synthetic speech representation of the corresponding training text utterance. The method also includes updating parameters of the GAN-based TTS model based on the adversarial loss term determined at each of the plurality of output steps for each training text utterance of the plurality of training text utterances.
    Type: Application
    Filed: November 11, 2021
    Publication date: March 3, 2022
    Applicant: Google LLC
    Inventors: Zhehuai Chen, Andrew M. Rosenberg, Bhuvana Ramabhadran, Pedro J. Moreno Mengibar
  • Patent number: 11222620
    Abstract: A method for training a generative adversarial network (GAN)-based text-to-speech (TTS) model and a speech recognition model in unison includes obtaining a plurality of training text utterances. At each of a plurality of output steps for each training text utterance, the method also includes generating, for output by the GAN-Based TTS model, a synthetic speech representation of the corresponding training text utterance, and determining, using an adversarial discriminator of the GAN, an adversarial loss term indicative of an amount of acoustic noise disparity in one of the non-synthetic speech representations selected from the set of spoken training utterances relative to the corresponding synthetic speech representation of the corresponding training text utterance. The method also includes updating parameters of the GAN-based TTS model based on the adversarial loss term determined at each of the plurality of output steps for each training text utterance of the plurality of training text utterances.
    Type: Grant
    Filed: May 7, 2020
    Date of Patent: January 11, 2022
    Assignee: Google LLC
    Inventors: Zhehuai Chen, Andrew M. Rosenberg, Bhuvana Ramabhadran, Pedro J. Moreno Mengibar
  • Publication number: 20210350786
    Abstract: A method for training a generative adversarial network (GAN)-based text-to-speech (TTS) model and a speech recognition model in unison includes obtaining a plurality of training text utterances. At each of a plurality of output steps for each training text utterance, the method also includes generating, for output by the GAN-Based TTS model, a synthetic speech representation of the corresponding training text utterance, and determining, using an adversarial discriminator of the GAN, an adversarial loss term indicative of an amount of acoustic noise disparity in one of the non-synthetic speech representations selected from the set of spoken training utterances relative to the corresponding synthetic speech representation of the corresponding training text utterance. The method also includes updating parameters of the GAN-based TTS model based on the adversarial loss term determined at each of the plurality of output steps for each training text utterance of the plurality of training text utterances.
    Type: Application
    Filed: May 7, 2020
    Publication date: November 11, 2021
    Applicant: Google LLC
    Inventors: Zhehuai Chen, Andrew M. Rosenberg, Bhuvana Ramabhadran, Pedro J. Moreno Mengibar
  • Publication number: 20200380952
    Abstract: A method includes receiving an input text sequence to be synthesized into speech in a first language and obtaining a speaker embedding, the speaker embedding specifying specific voice characteristics of a target speaker for synthesizing the input text sequence into speech that clones a voice of the target speaker. The target speaker includes a native speaker of a second language different than the first language. The method also includes generating, using a text-to-speech (TTS) model, an output audio feature representation of the input text by processing the input text sequence and the speaker embedding. The output audio feature representation includes the voice characteristics of the target speaker specified by the speaker embedding.
    Type: Application
    Filed: April 22, 2020
    Publication date: December 3, 2020
    Applicant: Google LLC
    Inventors: Yu Zhang, Ron J. Weiss, Byungha Chun, Yonghui Wu, Zhifeng Chen, Russell John Wyatt Skerry-Ryan, Ye Jia, Andrew M. Rosenberg, Bhuvana Ramabhadran
  • Patent number: 9093067
    Abstract: The subject matter of this specification can be implemented in a computer-implemented method that includes receiving utterances and transcripts thereof. The method includes analyzing the utterances and transcripts to determine certain attributes, such as distances between prosodic contours for pairs of utterances. A model can be generated that can be used to estimate a distance between a determined prosodic contour for a received utterance and an unknown prosodic contour for a synthesized utterance when given a distance between attributes for text associated with the received utterance and the synthesized utterance.
    Type: Grant
    Filed: November 26, 2012
    Date of Patent: July 28, 2015
    Assignee: Google Inc.
    Inventors: Martin Jansche, Michael D. Riley, Andrew M. Rosenberg, Terry Tai
  • Patent number: 8321225
    Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method including receiving text to be synthesized as a spoken utterance. The method includes analyzing the received text to determine attributes of the received text and selecting one or more utterances from a database based on a comparison between the attributes of the received text and attributes of text representing the stored utterances. The method includes determining, for each utterance, a distance between a contour of the utterance and a hypothetical contour of the spoken utterance, the determination based on a model that relates distances between pairs of contours of the utterances to relationships between attributes of text for the pairs. The method includes selecting a final utterance having a contour with a closest distance to the hypothetical contour and generating a contour for the received text based on the contour of the final utterance.
    Type: Grant
    Filed: November 14, 2008
    Date of Patent: November 27, 2012
    Assignee: Google Inc.
    Inventors: Martin Jansche, Michael D. Riley, Andrew M. Rosenberg, Terry Tai