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)
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:
Assignee:
ULSAN NAT INST SCIENCE & TECH UNIST (KR)
International Classes:
G10L15/26; G10L15/02; G10L15/16; G10L15/183; G10L15/22; G10L21/0208
Foreign References:
KR20210047173A | 2021-04-29 | |||
KR20150052600A | 2015-05-14 | |||
KR20200091797A | 2020-07-31 | |||
KR20190100498A | 2019-08-29 | |||
US20140249816A1 | 2014-09-04 |
Attorney, Agent or Firm:
G1 IP LAW FIRM (KR)
Download PDF: