Patents by Inventor Yanwei Pan

Yanwei Pan 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).

  • Training for long-form speech recognition
    Patent number: 12482453
    Abstract: A method includes obtaining a set of training samples, wherein each training sample includes a corresponding sequence of speech segments corresponding to a training utterance and a corresponding sequence of ground-truth transcriptions for the sequence of speech segments, and wherein each ground-truth transcription includes a start time and an end time of a corresponding speech segment. For each training sample in the set of training samples, the method includes processing, using a speech recognition model, the corresponding sequence of speech segments to obtain one or more speech recognition hypotheses for the training utterance; and, for each speech recognition hypothesis obtained for the training utterance, identifying a respective number of word errors relative to the corresponding sequence of ground-truth transcriptions.
    Type: Grant
    Filed: September 27, 2022
    Date of Patent: November 25, 2025
    Assignee: Google LLC
    Inventors: Zhiyun Lu, Thibault Doutre, Yanwei Pan, Liangliang Cao, Rohit Prabhavalkar, Trevor Strohman, Chao Zhang
  • TRAINING FOR LONG-FORM SPEECH RECOGNITION
    Publication number: 20230103382
    Abstract: A method includes obtaining a set of training samples, wherein each training sample includes a corresponding sequence of speech segments corresponding to a training utterance and a corresponding sequence of ground-truth transcriptions for the sequence of speech segments, and wherein each ground-truth transcription includes a start time and an end time of a corresponding speech segment. For each training sample in the set of training samples, the method includes processing, using a speech recognition model, the corresponding sequence of speech segments to obtain one or more speech recognition hypotheses for the training utterance; and, for each speech recognition hypothesis obtained for the training utterance, identifying a respective number of word errors relative to the corresponding sequence of ground-truth transcriptions.
    Type: Application
    Filed: September 27, 2022
    Publication date: April 6, 2023
    Applicant: Google LLC
    Inventors: Zhiyun Lu, Thibault Doutre, Yanwei Pan, Liangliang Cao, Rohit Prabhavalkar, Trevor Strohman, Chao Zhang