상세정보
학술지
변분 오토인코더와 비교사 데이터 증강을 이용한 음성인식기 준지도 학습
- 저자
- 조현호, 강병옥, 권오욱
- 발행일
- 202111
- 출처
- 한국음향학회지, v.40 no.6, pp.578-586
- ISSN
- 2287-3775
- 출판사
- 한국음향학회
- 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.
