BROWSE
Detail
Journal Article
변분 오토인코더와 비교사 데이터 증강을 이용한 음성인식기 준지도 학습
- Authors
- 조현호, 강병옥, 권오욱
- Issue Date
- 2021-11
- Citation
- 한국음향학회지, v.40, no.6, pp.578-586
- ISSN
- 2287-3775
- Publisher
- 한국음향학회
- Language
- Korean
- Type
- Journal Article
- Abstract
- 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 Keywords
- Computer simulation(MC and MD), Data Augmentation, End to End(E2E), Semi-Supervised Learning(SSL), Semi-Supervised learning method, Word Error Rate
This work is distributed under the term of Creative Commons License (CCL)
(CC BY NC)
(CC BY NC)
