Semi-Supervised Speech Recognition Acoustic Model Training Using Policy Gradient
Open Access
- 20 May 2020
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 10 (10) , 3542
Abstract
In this paper, we propose a policy gradient-based semi-supervised speech recognition acoustic model training. In practice, self-training and teacher/student learning are one of the widely used semi-supervised training methods due to their scalability and effectiveness. These methods are based on generating pseudo labels for unlabeled samples using a pre-trained model and selecting reliable samples using confidence measure. However, there are some considerations in this approach. The generated pseudo labels can be biased depending on which pre-trained model is used, and the training process can be complicated because the confidence measure is usually carried out in post-processing using external knowledge. Therefore, to address these issues, we propose a policy gradient method-based approach. Policy gradient is a reinforcement learning algorithm to find an optimal behavior strategy for an agent to obtain optimal rewards. The policy gradient-based approach provides a framework for exploring unlabeled data as well as exploiting labeled data, and it also provides a way to incorporate external knowledge in the same training cycle. The proposed approach was evaluated on an in-house non-native Korean recognition domain. The experimental results show that the method is effective in semi-supervised acoustic model training.Keywords
This publication has 22 references indexed in Scilit:
- Semi-Supervised Training in Deep Learning Acoustic Model2016
- Graph-Based Semisupervised Learning for Acoustic Modeling in Automatic Speech RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016
- Hybrid speech recognition with Deep Bidirectional LSTM2013
- Large scale deep neural network acoustic modeling with semi-supervised training data for YouTube video transcription2013
- Unsupervised training and directed manual transcription for LVCSRSpeech Communication, 2010
- Confidence measures for speech recognition: A surveySpeech Communication, 2005
- Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition2005
- Unsupervised training of acoustic models for large vocabulary continuous speech recognitionIEEE Transactions on Speech and Audio Processing, 2004
- Reinforcement Learning: A SurveyJournal of Artificial Intelligence Research, 1996
- Continuous speech recognition by statistical methodsProceedings of the IEEE, 1976