Patents by Inventor Eva Sharma

Eva Sharma 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).

  • GENERATING AND USING TEXT-TO-SPEECH DATA FOR SPEECH RECOGNITION MODELS
    Publication number: 20230186919
    Abstract: Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.
    Type: Application
    Filed: February 10, 2023
    Publication date: June 15, 2023
    Inventors: Guoli YE, Yan HUANG, Wenning WEI, Lei HE, Eva SHARMA, Jian WU, Yao TIAN, Edward C. LIN, Yifan GONG, Rui ZHAO, Jinyu LI, William Maxwell GALE
  • Generating and using text-to-speech data for speech recognition models
    Patent number: 11587569
    Abstract: Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.
    Type: Grant
    Filed: May 14, 2020
    Date of Patent: February 21, 2023
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Guoli Ye, Yan Huang, Wenning Wei, Lei He, Eva Sharma, Jian Wu, Yao Tian, Edward C. Lin, Yifan Gong, Rui Zhao, Jinyu Li, William Maxwell Gale
  • GENERATING AND USING TEXT-TO-SPEECH DATA FOR SPEECH RECOGNITION MODELS
    Publication number: 20210304769
    Abstract: Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.
    Type: Application
    Filed: May 14, 2020
    Publication date: September 30, 2021
    Inventors: Guoli Ye, Yan Huang, Wenning Wei, Lei He, Eva Sharma, Jian Wu, Yao Tian, Edward C. Lin, Yifan Gong, Rui Zhao, Jinyu Li, William Maxwell Gale