Next Article in Journal
Estimation of Wind Turbine Angular Velocity Remotely Found on Video Mining and Convolutional Neural Network
Previous Article in Journal
A Hierarchical Control System for Autonomous Driving towards Urban Challenges
Previous Article in Special Issue
Multi-Task Learning U-Net for Single-Channel Speech Enhancement and Mask-Based Voice Activity Detection
Open AccessArticle

Semi-Supervised Speech Recognition Acoustic Model Training Using Policy Gradient

Electronics and Telecommunications Research Institute, Daejeon 34129, Korea
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(10), 3542; https://doi.org/10.3390/app10103542
Received: 13 April 2020 / Revised: 18 May 2020 / Accepted: 18 May 2020 / Published: 20 May 2020
(This article belongs to the Special Issue Intelligent Speech and Acoustic Signal Processing)
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. View Full-Text
Keywords: speech recognition; semi-supervised training; reinforcement learning; policy gradient speech recognition; semi-supervised training; reinforcement learning; policy gradient
Show Figures

Figure 1

MDPI and ACS Style

Chung, H.; Lee, S.J.; Jeon, H.B.; Park, J.G. Semi-Supervised Speech Recognition Acoustic Model Training Using Policy Gradient. Appl. Sci. 2020, 10, 3542.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop