Patents by Inventor Nal Kalchbrenner

Nal Kalchbrenner 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).

  • SPEECH SYNTHESIS UTILIZING AUDIO WAVEFORM DIFFERENCE SIGNAL(S)
    Publication number: 20240161729
    Abstract: Techniques are disclosed that enable generation of an audio waveform representing synthesized speech based on a difference signal determined using an autoregressive model. Various implementations include using a distribution of the difference signal values to represent sounds found in human speech with a higher level of granularity than sounds not frequently found in human speech. Additional or alternative implementations include using one or more speakers of a client device to render the generated audio waveform.
    Type: Application
    Filed: January 19, 2024
    Publication date: May 16, 2024
    Inventors: Luis Carlos Cobo Rus, Nal Kalchbrenner, Erich Elsen, Chenjie Gu
  • Speech synthesis utilizing audio waveform difference signal(s)
    Patent number: 11915682
    Abstract: Techniques are disclosed that enable generation of an audio waveform representing synthesized speech based on a difference signal determined using an autoregressive model. Various implementations include using a distribution of the difference signal values to represent sounds found in human speech with a higher level of granularity than sounds not frequently found in human speech. Additional or alternative implementations include using one or more speakers of a client device to render the generated audio waveform.
    Type: Grant
    Filed: May 20, 2019
    Date of Patent: February 27, 2024
    Assignee: DeepMind Technologies Limited
    Inventors: Luis Carlos Cobo Rus, Nal Kalchbrenner, Erich Elsen, Chenjie Gu
  • SPEECH SYNTHESIS UTILIZING AUDIO WAVEFORM DIFFERENCE SIGNAL(S)
    Publication number: 20220254330
    Abstract: Techniques are disclosed that enable generation of an audio waveform representing synthesized speech based on a difference signal determined using an autoregressive model. Various implementations include using a distribution of the difference signal values to represent sounds found in human speech with a higher level of granularity than sounds not frequently found in human speech. Additional or alternative implementations include using one or more speakers of a client device to render the generated audio waveform.
    Type: Application
    Filed: May 20, 2019
    Publication date: August 11, 2022
    Inventors: Luis Carlos Cobo Rus, Nal Kalchbrenner, Erich Elsen, Chenjie Gu