Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
APPARATUS AND METHOD FOR PROVIDING SPEECH RECOGNITION SERVICE BY USING ARTIFICIAL INTELLIGENCE MODEL
Document Type and Number:
WIPO Patent Application WO/2023/003072
Kind Code:
A1
Abstract:
The present disclosure relates to a method for providing a speech recognition service by using an artificial intelligence model and an electronic device performing same. According to an embodiment, the method by which the electronic device provides a speech recognition service by using an artificial intelligence model may comprise the steps of: acquiring an audio signal including a user speech signal; preprocessing the acquired audio signal; acquiring a character string corresponding to the speech signal by inputting the preprocessed audio signal into an artificial intelligence model that outputs a character string corresponding to the speech signal when the preprocessed audio signal is input; on the basis of accuracy information regarding the character string acquired from the artificial intelligence model, determining a confidence level for the character string; and outputting the character string and the confidence level together.

Inventors:
LEE HUI SUNG (KR)
KIM BYOUNG HERN (KR)
PARK SU YOUNG (KR)
PARK HA EUN (KR)
KIM DONG YOON (KR)
Application Number:
PCT/KR2021/011523
Publication Date:
January 26, 2023
Filing Date:
August 27, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
ULSAN NAT INST SCIENCE & TECH UNIST (KR)
International Classes:
G10L15/26; G10L15/02; G10L15/16; G10L15/183; G10L15/22; G10L21/0208
Foreign References:
KR20210047173A2021-04-29
KR20150052600A2015-05-14
KR20200091797A2020-07-31
KR20190100498A2019-08-29
US20140249816A12014-09-04
Attorney, Agent or Firm:
G1 IP LAW FIRM (KR)
Download PDF: