Patents by Inventor Sergey Kishchenko

Sergey Kishchenko 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 recognition with sequence-to-sequence models
    Patent number: 11335333
    Abstract: A method includes obtaining audio data for a long-form utterance and segmenting the audio data for the long-form utterance into a plurality of overlapping segments. The method also includes, for each overlapping segment of the plurality of overlapping segments: providing features indicative of acoustic characteristics of the long-form utterance represented by the corresponding overlapping segment as input to an encoder neural network; processing an output of the encoder neural network using an attender neural network to generate a context vector; and generating word elements using the context vector and a decoder neural network. The method also includes generating a transcription for the long-form utterance by merging the word elements from the plurality of overlapping segments and providing the transcription as an output of the automated speech recognition system.
    Type: Grant
    Filed: December 17, 2019
    Date of Patent: May 17, 2022
    Assignee: Google LLC
    Inventors: Wei Han, Chung-Cheng Chiu, Yu Zhang, Yonghui Wu, Patrick Nguyen, Sergey Kishchenko
  • SPEECH RECOGNITION WITH SEQUENCE-TO-SEQUENCE MODELS
    Publication number: 20200126538
    Abstract: A method includes obtaining audio data for a long-form utterance and segmenting the audio data for the long-form utterance into a plurality of overlapping segments. The method also includes, for each overlapping segment of the plurality of overlapping segments: providing features indicative of acoustic characteristics of the long-form utterance represented by the corresponding overlapping segment as input to an encoder neural network; processing an output of the encoder neural network using an attender neural network to generate a context vector; and generating word elements using the context vector and a decoder neural network. The method also includes generating a transcription for the long-form utterance by merging the word elements from the plurality of overlapping segments and providing the transcription as an output of the automated speech recognition system.
    Type: Application
    Filed: December 17, 2019
    Publication date: April 23, 2020
    Applicant: Google LLC
    Inventors: Wei Han, Chung-Cheng Chiu, Yu Zhang, Yonghui Wu, Patrick Nguyen, Sergey Kishchenko