Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
SPEECH RECOGNITION SYSTEM AND METHOD FOR AUTOMATICALLY CALIBRATING DATA LABEL
Document Type and Number:
WIPO Patent Application WO/2022/030805
Kind Code:
A1
Abstract:
Proposed are a speech recognition system and method for automatically calibrating a data label. A speech recognition method for automatically calibrating a data label according to an embodiment may comprise the steps of: performing confidence-based filtering to find the location of occurrence of a wrong label in time-series speech data, in which a correct label and the wrong label are temporally mixed, by using a transformer-based speech recognition model; and after performing filtering, replacing a label at a decoder time step, which has been determined to be a wrong label by the location of occurrence of the wrong label, so as to improve the performance of the transformer-based speech recognition model, wherein the step of performing confidence-based filtering to find the location of occurrence of the wrong label in the time-series speech data comprises finding and calibrating the wrong label using the confidence obtained by using a transition probability between labels at every decoder time step.

Inventors:
CHANG JOON-HYUK (KR)
LEE JAEHONG (KR)
Application Number:
PCT/KR2021/009250
Publication Date:
February 10, 2022
Filing Date:
July 19, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
IUCF HYU (KR)
International Classes:
G10L19/005; G10L15/14; G10L19/26; G10L21/02
Foreign References:
JP2012078775A2012-04-19
JPH06110493A1994-04-22
KR100996212B12010-11-24
KR19980076348A1998-11-16
Attorney, Agent or Firm:
YANG, Sungbo (KR)
Download PDF: