Patents by Inventor Xiaoqiang Xiao

Xiaoqiang Xiao 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).

  • Patent number: 11432150
    Abstract: A system and method for authenticating network access of a terminal is described. The method may include sending, by the terminal, a user identity authentication request including first authentication information and second authentication information to an authentication server, where the first authentication information is used to authenticate a user identity of the terminal, and the second authentication information is used to determine a platform corresponding to the terminal. The method may also include after receiving user identity authentication acknowledgment information sent by the authentication server, sending, by the terminal to the authentication server, a platform identity authentication request including third authentication information used to determine the platform corresponding to the terminal.
    Type: Grant
    Filed: April 29, 2020
    Date of Patent: August 30, 2022
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Xiaoqiang Du, Bo Zhao, Yu Xiao
  • Patent number: 10062374
    Abstract: According to some aspects, a method of training a transformation component using a trained acoustic model comprising first parameters having respective first values established during training of the acoustic model using first training data is provided. The method comprises using at least one computer processor to perform coupling the transformation component to a portion of the acoustic model, the transformation component comprising second parameters, and training the transformation component by determining, for the second parameters, respective second values using second training data input to the transformation component and processed by the acoustic model, wherein the acoustic model retains the first parameters having the respective first values throughout training of the transformation component.
    Type: Grant
    Filed: July 18, 2014
    Date of Patent: August 28, 2018
    Assignee: Nuance Communications, Inc.
    Inventors: Xiaoqiang Xiao, Chengyuan Ma, Venkatesh Nagesha
  • Patent number: 9269349
    Abstract: An automatic speech recognition dictation application is described that includes a dictation module for performing automatic speech recognition in a dictation session with a speaker user to determine representative text corresponding to input speech from the speaker user. A post-processing module develops a session level metric correlated to verbatim recognition error rate of the dictation session, and determines if recognition performance degraded during the dictation session based on a comparison of the session metric to a baseline metric.
    Type: Grant
    Filed: May 24, 2012
    Date of Patent: February 23, 2016
    Assignee: Nuance Communications, Inc.
    Inventors: Xiaoqiang Xiao, Venkatesh Nagesha
  • Publication number: 20160019884
    Abstract: According to some aspects, a method of training a transformation component using a trained acoustic model comprising first parameters having respective first values established during training of the acoustic model using first training data is provided. The method comprises using at least one computer processor to perform coupling the transformation component to a portion of the acoustic model, the transformation component comprising second parameters, and training the transformation component by determining, for the second parameters, respective second values using second training data input to the transformation component and processed by the acoustic model, wherein the acoustic model retains the first parameters having the respective first values throughout training of the transformation component.
    Type: Application
    Filed: July 18, 2014
    Publication date: January 21, 2016
    Inventors: Xiaoqiang Xiao, Chengyuan Ma, Venkatesh Nagesha
  • Publication number: 20130317820
    Abstract: An automatic speech recognition dictation application is described that includes a dictation module for performing automatic speech recognition in a dictation session with a speaker user to determine representative text corresponding to input speech from the speaker user. A post-processing module develops a session level metric correlated to verbatim recognition error rate of the dictation session, and determines if recognition performance degraded during the dictation session based on a comparison of the session metric to a baseline metric.
    Type: Application
    Filed: May 24, 2012
    Publication date: November 28, 2013
    Applicant: NUANCE COMMUNICATIONS, INC.
    Inventors: Xiaoqiang Xiao, Venkatesh Nagesha
  • Publication number: 20110224982
    Abstract: Described is a technology in which information retrieval (IR) techniques are used in a speech recognition (ASR) system. Acoustic units (e.g., phones, syllables, multi-phone units, words and/or phrases) are decoded, and features found from those acoustic units. The features are then used with IR techniques (e.g., TF-IDF based retrieval) to obtain a target output (a word or words).
    Type: Application
    Filed: March 12, 2010
    Publication date: September 15, 2011
    Applicant: c/o Microsoft Corporation
    Inventors: Alejandro Acero, James Garnet Droppo, III, Xiaoqiang Xiao, Geoffrey G. Zweig