Hyung-Bae Jeon

Hyung-Bae Jeon

Auto-generated profile, based on publicly available information

Hyung-Bae Jeon

Electronics and Telecommunications Research Institute, Daejeon 34129, Korea

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 March 2016 in ETRI Journal
Verified
Journal Article
Closed access
PDF file
HJHyung-Bae Jeon
Hyung-Bae Jeon
SLSoo-Young Lee
Soo-Young Lee

20 May 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HCHoon Chung
Hoon Chung
SLSung Joo Lee
Sung Joo Lee
HJHyeong Bae Jeon
Hyeong Bae Jeon
JPJeon Gue Park
Jeon Gue Park
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.

4 September 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
BKByung Ok Kang
Byung Ok Kang
HJHyeong Bae Jeon
Hyeong Bae Jeon
JPJeon Gue Park
Jeon Gue Park
We propose two approaches to handle speech recognition for task domains with sparse matched training data. One is an active learning method that selects training data for the target domain from another general domain that already has a significant amount of labeled speech data. This method uses attribute-disentangled latent variables. For the active learning process, we designed an integrated system consisting of a variational autoencoder with an encoder that infers latent variables with disentangled attributes from the input speech, and a classifier that selects training data with attributes matching the target domain. The other method combines data augmentation methods for generating matched target domain speech data and transfer learning methods based on teacher/student learning. To evaluate the proposed method, we experimented with various task domains with sparse matched training data. The experimental results show that the proposed method has qualitative characteristics that are suitable for the desired purpose, it outperforms random selection, and is comparable to using an equal amount of additional target domain data.

1 January 2017
Verified
Conference Paper
Open access
YOYoo Rhee Oh
Yoo Rhee Oh
HJHyung-Bae Jeon
Hyung-Bae Jeon
HSHwa Jeon Song
Hwa Jeon Song
YLYun-Kyung Lee
Yun-Kyung Lee
JPJeon-Gue Park
Jeon-Gue Park

6 December 2013 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
KKKwang-Ho Kim
Kwang-Ho Kim
DJDae-Young Jung
Dae-Young Jung
DLDonghyun Lee
Donghyun Lee
HLHyuk-Jun Lee
Hyuk-Jun Lee
Sungyong ParkSungyong Park
Sungyong Park
YLYun-Keun Lee
Yun-Keun Lee

12 August 2011
Verified
Book Chapter
Closed access
PDF file
ECEuisok Chung
Euisok Chung
HJHyung-Bae Jeon
Hyung-Bae Jeon
JPJeon-Gue Park
Jeon-Gue Park
YLYun-Keun Lee
Yun-Keun Lee