Volgen
Shigeru Katagiri
Shigeru Katagiri
Onbekend partnerschap
Geverifieerd e-mailadres voor mbj.ocn.ne.jp
Titel
Geciteerd door
Geciteerd door
Jaar
Discriminative learning for minimum error classification (pattern recognition)
BH Juang, S Katagiri
IEEE Transactions on signal processing 40 (12), 3043-3054, 1992
10851992
ATR Japanese speech database as a tool of speech recognition and synthesis
A Kurematsu, K Takeda, Y Sagisaka, S Katagiri, H Kuwabara, K Shikano
Speech communication 9 (4), 357-363, 1990
3581990
Pattern recognition using a family of design algorithms based upon the generalized probabilistic descent method
S Katagiri, BH Juang, CH Lee
Proceedings of the IEEE 86 (11), 2345-2373, 1998
2431998
Discriminative training for large-vocabulary speech recognition using minimum classification error
E McDermott, TJ Hazen, J Le Roux, A Nakamura, S Katagiri
IEEE Transactions on Audio, Speech, and Language Processing 15 (1), 203-223, 2006
2132006
New discriminative training algorithms based on the generalized probabilistic descent method
S Katagiri, CH Lee, BH Juang
Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop …, 1991
1861991
Confusion-matrix-based kernel logistic regression for imbalanced data classification
M Ohsaki, P Wang, K Matsuda, S Katagiri, H Watanabe, A Ralescu
IEEE Transactions on Knowledge and Data Engineering 29 (9), 1806-1819, 2017
1182017
An application of discriminative feature extraction to filter-bank-based speech recognition
A Biem, S Katagiri, E McDermott, BH Juang
IEEE Transactions on Speech and Audio Processing 9 (2), 96-110, 2001
1102001
Signal pattern recognition apparatus comprising parameter training controller for training feature conversion parameters and discriminant functions
H Watanabe, T Yamaguchi, S Katagiri
US Patent 5,754,681, 1998
1081998
Shift-invariant, multi-category phoneme recognition using Kohonen's LVQ2
E McDermott, S Katagiri
International Conference on Acoustics, Speech, and Signal Processing,, 81-84, 1989
981989
Nonlinear dynamical systems: feedforward neural network perspectives
IW Sandberg, JT Lo, CL Fancourt, JC Principe, S Katagiri, S Haykin
John Wiley & Sons, 2001
952001
A large-scale Japanese speech database.
Y Sagisaka, K Takeda, M Abel, S Katagiri, T Umeda, H Kuwabara
ICSLP, 1089-1092, 1990
921990
Feature extraction based on minimum classification error/generalized probabilistic descent method
A Biem, S Katagiri
1993 IEEE International Conference on Acoustics, Speech, and Signal …, 1993
861993
Pattern recognition using discriminative feature extraction
A Biem, S Katagiri, BH Juang
IEEE Transactions on Signal Processing 45 (2), 500-504, 1997
771997
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
762014
Handbook of neural networks for speech processing
S Katagiri
Artech House, Inc., 2000
752000
A generalized probabilistic descent method
S Katagiri
ASJ, Fall Conf., Nagoya, Japan, 1990, 1990
731990
Networks for speech enhancement
EA Wan, AT Nelson
Handbook of neural networks for speech processing. Artech House, Boston, USA …, 1999
721999
A new hybrid algorithm for speech recognition based on HMM segmentation and learning vector quantization
S Katagiri, CH Lee
IEEE Transactions on Speech and Audio Processing 1 (4), 421-430, 1993
711993
Prototype-based minimum classification error/generalized probabilistic descent training for various speech units
E McDermott, S Katagiri
Computer Speech & Language 8 (4), 351-368, 1994
691994
A hybrid speech recognition system using HMMs with an LVQ-trained codebook
H Iwamida, S Katagiri, E McDermott, Y Tohkura
Journal of the Acoustical Society of Japan (E) 11 (5), 277-286, 1990
661990
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20