Patents by Inventor Sangyoun Paik

Sangyoun Paik 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).

  • METHOD FOR ERROR DETECTION BY USING TOP-DOWN METHOD
    Publication number: 20230419028
    Abstract: Disclosed is a method for error detection, performed by one or more processors of a computing device according to an example embodiment of the present disclosure. The method includes evaluating an error rate for a sentence to be evaluated, in a first language unit. the method includes evaluating an error rate in a second language unit which is smaller than the first language unit, based on the first language unit error.
    Type: Application
    Filed: October 20, 2022
    Publication date: December 28, 2023
    Inventors: Hwanbok MUN, Sangyoun PAIK, Subong CHOI, Dongchan SHIN, Jihwa LEE
  • Method for error detection by using top-down method
    Patent number: 11841737
    Abstract: Disclosed is a method for error detection, performed by one or more processors of a computing device according to an example embodiment of the present disclosure. The method includes evaluating an error rate for a sentence to be evaluated, in a first language unit. the method includes evaluating an error rate in a second language unit which is smaller than the first language unit, based on the first language unit error.
    Type: Grant
    Filed: October 20, 2022
    Date of Patent: December 12, 2023
    Assignee: ACTIONPOWER CORP.
    Inventors: Hwanbok Mun, Sangyoun Paik, Subong Choi, Dongchan Shin, Jihwa Lee
  • Method for generating learning data for speech recognition error detection
    Patent number: 11721325
    Abstract: Disclosed is a method for generating data, the method is performed by one or more processors of a computing device. The method may include: segmenting text data generated based on speech information into a token unit; generating a first feature vector based on the text data segmented into the token unit, and generating a first label vector corresponding to the generated first feature vector, and generating a second feature vector and a second label vector by performing mix-up for each of the generated first feature vector and the generated first label vector.
    Type: Grant
    Filed: July 27, 2022
    Date of Patent: August 8, 2023
    Assignee: ActionPower Corp.
    Inventors: Seongmin Park, Dongchan Shin, Sangyoun Paik, Subong Choi, Alena Kazakova, Jihwa Lee