ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 변분 오토인코더와 비교사 데이터 증강을 이용한 음성인식기 준지도 학습
Cited 0 time in scopus Download 120 time Share share facebook twitter linkedin kakaostory
저자
조현호, 강병옥, 권오욱
발행일
202111
출처
한국음향학회지, v.40 no.6, pp.578-586
ISSN
2287-3775
출판사
한국음향학회
DOI
https://dx.doi.org/10.7776/ASK.2021.40.6.578
협약과제
21HS2800, 준지도학습형 언어지능 원천기술 및 이에 기반한 외국인 지원용 한국어 튜터링 서비스 개발, 이윤근
초록
We propose a semi-supervised learning method based on Variational AutoEncoder (VAE) and Unsupervised Data Augmentation (UDA) to improve the performance of an end-to-end speech recognizer. In the proposed method, first, the VAE-based augmentation model and the baseline end-to-end speech recognizer are trained using the original speech data. Then, the baseline end-to-end speech recognizer is trained again using data augmented from the learned augmentation model. Finally, the learned augmentation model and end-to-end speech recognizer are re-learned using the UDA-based semi-supervised learning method. As a result of the computer simulation, the augmentation model is shown to improve the Word Error Rate (WER) of the baseline end-to-end speech recognizer, and further improve its performance by combining it with the UDA-based learning method.
KSP 제안 키워드
Computer simulation(MC and MD), Data Augmentation, End to End(E2E), Semi-Supervised Learning(SSL), Semi-Supervised learning method, word error rate
본 저작물은 크리에이티브 커먼즈 저작자 표시 - 비영리 (CC BY NC) 조건에 따라 이용할 수 있습니다.
저작자 표시 - 비영리 (CC BY NC)