Patents by Inventor Chaojun Liu

Chaojun Liu 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).

  • Discriminative training for speaker and speech verification
    Patent number: 7454339
    Abstract: A method for discriminatively training acoustic models is provided for automated speaker verification (SV) and speech (or utterance) verification (UV) systems.
    Type: Grant
    Filed: December 20, 2005
    Date of Patent: November 18, 2008
    Assignee: Panasonic Corporation
    Inventors: Chaojun Liu, David Kryze, Luca Rigazio
  • Discriminative training for speaker and speech verification
    Publication number: 20070143109
    Abstract: A method for discriminatively training acoustic models is provided for automated speaker verification (SV) and speech (or utterance) verification (UV) systems.
    Type: Application
    Filed: December 20, 2005
    Publication date: June 21, 2007
    Applicant: Matsushita Electric Industrial Co., Ltd.
    Inventors: Chaojun Liu, David Kryze, Luca Rigazio
  • Discriminative training of HMM models using maximum margin estimation for speech recognition
    Publication number: 20070083373
    Abstract: An improved discriminative training method is provided for hidden Markov models. The method includes: defining a measure of separation margin for the data; identifying a subset of training utterances having utterances misrecognized by the models; defining a training criterion for the models based on maximizing the separation margin; formulating the training criterion as a constrained minimax optimization problem; and solving the constrained minimax optimization problem over the subset of training utterances, thereby discriminatively training the models.
    Type: Application
    Filed: October 11, 2005
    Publication date: April 12, 2007
    Applicant: Matsushita Electric Industrial Co., Ltd.
    Inventors: Chaojun Liu, David Kryze, Luca Rigazio