Patents by Inventor Christophe J. VAN GYSEL

Christophe J. VAN GYSEL 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).

  • Rank-reduced token representation for automatic speech recognition
    Patent number: 10593346
    Abstract: The present disclosure generally relates to processing speech or text using rank-reduced token representation. In one example process, speech input is received. A sequence of candidate words corresponding to the speech input is determined. The sequence of candidate words includes a current word and one or more previous words. A vector representation of the current word is determined from a set of trained parameters. A number of parameters in the set of trained parameters varies as a function of one or more linguistic characteristics of the current word. Using the vector representation of the current word, a probability of a next word given the current word and the one or more previous words is determined. A text representation of the speech input is displayed based on the determined probability.
    Type: Grant
    Filed: March 15, 2017
    Date of Patent: March 17, 2020
    Assignee: Apple Inc.
    Inventors: Christophe J. Van Gysel, Yi Su, Xiaochuan Niu, Ilya Oparin
  • RANK-REDUCED TOKEN REPRESENTATION FOR AUTOMATIC SPEECH RECOGNITION
    Publication number: 20180182376
    Abstract: The present disclosure generally relates to processing speech or text using rank-reduced token representation. In one example process, speech input is received. A sequence of candidate words corresponding to the speech input is determined. The sequence of candidate words includes a current word and one or more previous words. A vector representation of the current word is determined from a set of trained parameters. A number of parameters in the set of trained parameters varies as a function of one or more linguistic characteristics of the current word. Using the vector representation of the current word, a probability of a next word given the current word and the one or more previous words is determined. A text representation of the speech input is displayed based on the determined probability.
    Type: Application
    Filed: March 15, 2017
    Publication date: June 28, 2018
    Inventors: Christophe J. VAN GYSEL, Yi SU, Xiaochuan NIU, Ilya OPARIN