Rchr
J-GLOBAL ID：201801020575169782
Update date: Sep. 01, 2020
SHEN PENG
SHEN PENG
Affiliation and department：
Research field (1)：
Perceptual information processing
Research keywords (4)：
Multi-modal speech recognition
, Event detection
, Language identification
, Speech recognition
Papers (23)：
-
Xugang Lu, Peng Shen, Sheng Li, Yu Tsao, Hisashi Kawai. Class-wise centroid distance metric learning for acoustic event detection. in Proc. of Interspeech. 2019
-
Sheng Li, Xugang Lu, Chenchen Ding, Peng Shen, Tatsuya Kawahara, Hisashi Kawai. Investigating radical-based end-to-end speech recognition systems for Chinese dialects and Japanese. in Proc. of Interspeech. 2019
-
Sheng Li, Chenchen Ding, Xugang Lu, Peng Shen, Tatsuya Kawahara, Hisashi Kawai. End-to-End articulatory attribute modeling for low-resource multilingual speech recognition. in Proc. of Interspeech. 2019
-
Sheng Li, Raj Dabre, Xugang Lu, Peng Shen, Tatsuya Kawahara, Hisashi Kawai. Improving transformer-based speech recognition systems with compressed structure and speech attributes augmentation. in Proc. of Interspeech. 2019
-
Peng Shen, Xugang Lu, Sheng Li, Hisashi Kawai. Interactive learning of teacher-student model for short utterance spoken language identification. in Proc. of IEEE-ICASSP. 2019
ｍore...
MISC (11)：
-
Peng Shen, Xugang Lu, Sheng Li, Hisashi Kawai. Investigation of multi-domain training for speech recognition. Spring Meeting of Acoustical Society of Japan. 2019
-
Sheng Li, Xugang Lu, Ryoichi Takashima, Peng Shen, Hisashi Kawai. Improving CTC-based acoustic model with very deep residual neural networks. Spring Meeting of Acoustical Society of Japan. 2018
-
Sheng Li, Xugang Lu, Ryoichi Takashima, Peng Shen, Hisashi Kawai. An empirical comparison of sequence training methods for the very deep residual time-delay neural network. Autumn Meeting of Acoustical Society of Japan. 2018
-
Peng Shen, Xugang Lu, Sheng Li, Hisashi Kawai. Short utterance-based spoken language identification. Autumn Meeting of Acoustical Society of Japan. 2018
-
Sheng Li, Xugang Lu, Peng Shen, Hisashi Kawai. Very deep convolutional residual network acoustic models for Japanese lecture transcription. Autumn Meeting of Acoustical Society of Japan. 2017
ｍore...
Education (1)：
- 2007 - 2013 Gifu University
Professional career (1)：
Work history (1)：
- 2014 - 現在 National Institute of Information and Communications Technology
Awards (2)：
- 2015/04 - NICT 団体優秀賞
- 2014/12 - 音声翻訳国際ワークショップ 英語認識評価世界一
Association Membership(s) (2)：
ISCA
, ACOUSTICAL SOCIETY OF JAPAN
