Follow
Shigeki  Matsuda
Shigeki Matsuda
COTOBA DESIGN
Verified email at metamoji.com
Title
Cited by
Cited by
Year
Speech enhancement based on deep denoising autoencoder.
X Lu, Y Tsao, S Matsuda, C Hori
Interspeech 2013, 436-440, 2013
10322013
Speaker adaptive training using deep neural networks
T Ochiai, S Matsuda, X Lu, C Hori, S Katagiri
2014 IEEE international conference on acoustics, speech and signal …, 2014
812014
Ensemble modeling of denoising autoencoder for speech spectrum restoration.
X Lu, Y Tsao, S Matsuda, C Hori
Interspeech 14, 885-889, 2014
752014
Context-dependent substroke model for HMM-based on-line handwriting recognition
J Tokuno, N Inami, S Matsuda, M Nakai, H Shimodaira, S Sagayama
Proceedings Eighth International Workshop on Frontiers in Handwriting …, 2002
542002
CENSREC-1-AV: An audio-visual corpus for noisy bimodal speech recognition
S Tamura, C Miyajima, N Kitaoka, T Yamada, S Tsuge, T Takiguchi, ...
Training 720, 480, 2010
512010
Sparse representation based on a bag of spectral exemplars for acoustic event detection
X Lu, Y Tsao, S Matsuda, C Hori
2014 IEEE International Conference on Acoustics, Speech and Signal …, 2014
502014
CENSREC-4: development of evaluation framework for distant-talking speech recognition under reverberant environments.
M Nakayama, T Nishiura, Y Denda, N Kitaoka, K Yamamoto, T Yamada, ...
INTERSPEECH, 968-971, 2008
412008
CENSREC-1-C: An evaluation framework for voice activity detection under noisy environments
N Kitaoka, T Yamada, S Tsuge, C Miyajima, K Yamamoto, T Nishiura, ...
Acoustical Science and Technology 30 (5), 363-371, 2009
402009
A robust speech recognition system for communication robots in noisy environments
CT Ishi, S Matsuda, T Kanda, T Jitsuhiro, H Ishiguro, S Nakamura, ...
IEEE Transactions on Robotics 24 (3), 759-763, 2008
402008
Speech restoration based on deep learning autoencoder with layer-wised pretraining.
X Lu, S Matsuda, C Hori, H Kashioka
Interspeech 2012, 1504-1507, 2012
392012
Multilingual speech-to-speech translation system: Voicetra
S Matsuda, X Hu, Y Shiga, H Kashioka, C Hori, K Yasuda, H Okuma, ...
2013 IEEE 14th International Conference on Mobile Data Management 2, 229-233, 2013
372013
Factored language model based on recurrent neural network
Y Wu, X Lu, H Yamamoto, S Matsuda, C Hori, H Kashioka
Proceedings of COLING 2012, 2835-2850, 2012
362012
Statistical acoustic model adaptation method, acoustic model learning method suitable for statistical acoustic model adaptation, storage medium storing parameters for building …
S Matsuda, LU Xugang
US Patent 10,629,185, 2020
332020
Automatic node selection for deep neural networks using group lasso regularization
T Ochiai, S Matsuda, H Watanabe, S Katagiri
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
312017
Robust speech recognition system for communication robots in real environments
CT Ishi, S Matsuda, T Kanda, T Jitsuhiro, H Ishiguro, S Nakamura, ...
2006 6th IEEE-RAS International Conference on Humanoid Robots, 340-345, 2006
312006
Deep neural network learning method and apparatus, and category-independent sub-network learning apparatus
S Matsuda, LU Xugang, C Hori, H Kashioka
US Patent 9,691,020, 2017
302017
Detecting robot-directed speech by situated understanding in physical interaction
X Zuo, N Iwahashi, K Funakoshi, M Nakano, R Taguchi, S Matsuda, ...
Information and Media Technologies 5 (4), 1314-1326, 2010
222010
ATR parallel decoding based speech recognition system robust to noise and speaking styles
S Matsuda, T Jitsuhiro, K Markov, S Nakamura
IEICE transactions on Information and Systems 89 (3), 989-997, 2006
212006
The NICT ASR system for IWSLT2012
H Yamamoto, Y Wu, CL Huang, X Lu, P Dixon, S Matsuda, C Hori, ...
Proceedings of the 9th International Workshop on Spoken Language Translation …, 2012
202012
Speech recognition system robust to noise and speaking styles.
S Matsuda, T Jitsuhiro, K Markov, S Nakamura
INTERSPEECH, 2817-2820, 2004
192004
The system can't perform the operation now. Try again later.
Articles 1–20