Hideyuki Watanabe

Publication Activity (10 Years)

Years Active: 1991-2021
Publications (10 Years): 15

Top Topics

Confusion Matrix

Speech Recognizer

Kernel Logistic Regression

Top Venues

J. Signal Process. Syst.

Publications

David Ha, Shigeru Katagiri, Hideyuki Watanabe, Miho Ohsaki
An Improved Boundary Uncertainty-Based Estimation for Classifier Evaluation. J. Signal Process. Syst. 93 (9) (2021)
David Ha, Yuya Tomotoshi, Masahiro Senda, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki
A Practical Method Based on Bayes Boundary-Ness for Optimal Classifier Parameter Status Selection. J. Signal Process. Syst. 92 (2) (2020)
Masahiro Senda, David Ha, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki
Maximum Bayes Boundary-Ness Training For Pattern Classification. SPML (2019)
Yuya Tomotoshi, David Ha, Emilie Delattre, Hideyuki Watanabe, Xugang Lu, Shigeru Katagiri, Miho Ohsaki
Optimal Classifier Parameter Status Selection Based on Bayes Boundary-ness for Multi-ProtoType and Multi-Layer Perceptron Classifiers. IUKM (2019)
Naoto Umezaki, Takumi Okubo, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki
Minimum Classification Error Training with Speech Synthesis-Based Regularization for Speech Recognition. SPML (2019)
David Ha, Emilie Delattre, Yuya Tomotoshi, Masahiro Senda, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki
Optimal Classifier Model Status Selection using Bayes boundary uncertainty. MLSP (2018)
David Ha, Hideyuki Watanabe, Yuya Tomotoshi, Emilie Delattre, Shigeru Katagiri
Optimality Analysis of Boundary-Uncertainty-Based Classifier Model Parameter Status Selection Method. SPML (2018)
Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Shigeru Katagiri
Automatic node selection for Deep Neural Networks using Group Lasso regularization. ICASSP (2017)
Ryoma Tani, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki
Compact kernel classifiers trained with minimum classification error criterion. MLSP (2017)
Miho Ohsaki, Peng Wang, Kenji Matsuda, Shigeru Katagiri, Hideyuki Watanabe, Anca Ralescu
Confusion-Matrix-Based Kernel Logistic Regression for Imbalanced Data Classification. IEEE Trans. Knowl. Data Eng. 29 (9) (2017)
Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Shigeru Katagiri
Automatic Node Selection for Deep Neural Networks using Group Lasso Regularization. CoRR (2016)
Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Hisashi Kawai, Shigeru Katagiri
Bottleneck linear transformation network adaptation for speaker adaptive training-based hybrid DNN-HMM speech recognizer. ICASSP (2016)
Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Chiori Hori, Hisashi Kawai, Shigeru Katagiri
Speaker Adaptive Training Localizing Speaker Modules in DNN for Hybrid DNN-HMM Speech Recognizers. IEICE Trans. Inf. Syst. (10) (2016)
Miho Ohsaki, Kenji Matsuda, Peng Wang, Shigeru Katagiri, Hideyuki Watanabe
Formulation of the kernel logistic regression based on the confusion matrix. CEC (2015)
Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Chiori Hori, Shigeru Katagiri
Speaker adaptive training for deep neural networks embedding linear transformation networks. ICASSP (2015)
Hideyuki Watanabe, Jun'ichi Tokuno, Tsukasa Ohashi, Shigeru Katagiri, Miho Ohsaki, Shigeki Matsuda, Hideki Kashioka
Minimum Classification Error Training Incorporating Automatic Loss Smoothness Determination. J. Signal Process. Syst. 74 (3) (2014)
Hideyuki Watanabe, Tsukasa Ohashi, Shigeru Katagiri, Miho Ohsaki, Shigeki Matsuda, Hideki Kashioka
Robust and Efficient Pattern Classification using Large Geometric Margin Minimum Classification Error Training. J. Signal Process. Syst. 74 (3) (2014)
Tsukasa Ohashi, Hideyuki Watanabe, Jun'ichi Tokuno, Shigeru Katagiri, Miho Ohsaki, Shigeki Matsuda, Hideki Kashioka
Increasing virtual samples through loss smoothness determination in large geometric margin minimum classification error training. ICASSP (2012)
Shigeru Katagiri, Hideyuki Watanabe
Minimum classification error vs. maximum margin: How should we penalize unseen samples? CIP (2012)
Hideyuki Watanabe, Jun'ichi Tokuno, Tsukasa Ohashi, Shigeru Katagiri, Miho Ohsaki
Minimum classification error training with automatic setting of loss smoothness. MLSP (2011)
Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki
Minimum classification error training with geometric margin enhancement for robust pattern recognition. MLSP (2011)
Hideyuki Watanabe, Shigeru Katagiri, Kouta Yamada, Erik McDermott, Atsushi Nakamura, Shinji Watanabe, Miho Ohsaki
Minimum Error Classification with geometric margin control. ICASSP (2010)
Nobuhiro Oda, Shoji Kido, Shoko Yamada, Takatoshi Aoki, Hideyuki Watanabe, Yukunori Korogi, Shigehiko Katsuragawa, Kunio Doi
Computer-aided diagnosis for distinction between benign and malignant pulmonary nodules on chest radiographs using temporal subtraction images. CARS (2004)
Chiyomi Miyajima, Hideyuki Watanabe, Keiichi Tokuda, Tadashi Kitamura, Shigeru Katagiri
A new approach to designing a feature extractor in speaker identification based on discriminative feature extraction. Speech Commun. 35 (3-4) (2001)
Chiyomi Miyajima, Hideyuki Watanabe, Tadashi Kitamura, Shigeru Katagiri
Speaker recognition based on discriminative feature extraction - optimization of mel-cepstral features using second-order all-pass warping function. EUROSPEECH (1999)
Hideyuki Watanabe, Yuji Matsumoto, Satoru Tanaka, Shigeru Katagiri
A new approach to acoustic signal monitoring based on the generalized probabilistic descent method. IEEE Trans. Signal Process. 47 (9) (1999)
Kazuhiko Uchida, Hideyuki Watanabe, Takatoshi Aoki, Katsumi Nakamura, Hajime Nakata
Clinical evaluation of irreversible data compression for computed radiography of the hand. J. Digit. Imaging 11 (3) (1998)
Kanji Egashira, Hajime Nakata, Hideyuki Watanabe, Kazuhiko Uchida, Katsumi Nakamura, Yoichi Ishino, Kenji Horino, Rie Yoshikawa
Clinical evaluation of irreversible data compression for computed radiography of the chest. J. Digit. Imaging 11 (4) (1998)
Hideyuki Watanabe, Yuji Matsumoto, Shigeru Katagiri
Minimum detection error training for acoustic signal monitoring. ICASSP (1998)
Hideyuki Watanabe, Tsuyoshi Yamaguchi, Shigeru Katagiri
Discriminative metric design for robust pattern recognition. IEEE Trans. Signal Process. 45 (11) (1997)
Hideyuki Watanabe, Shigeru Katagiri
HMM speech recognizer based on discriminative metric design. ICASSP (1997)
Jin'ichi Murakami, Hideyuki Watanabe, Masahide Sugiyama
Study of unknown-multiple signal-source clustering problem using ergodic HMM. Systems and Computers in Japan 27 (5) (1996)
Kazuhiko Uchida, Katsumi Nakamura, Hideyuki Watanabe, Kanji Egashira, Yoichi Ishino, Minoru Murakami, Hajime Nakata
Clinical evaluation of irreversible data compression for computed radiography in excretory urography. J. Digit. Imaging 9 (3) (1996)
Jin'ichi Murakami, Masahide Sugiyama, Hideyuki Watanabe
Unknown-multiple signal source clustering problem using ergodic HMM and applied to speaker classification. ICSLP (1996)
Hideyuki Watanabe, Tsuyoshi Yamaguchi, Shigeru Katagiri
Discriminative metric design for pattern recognition. ICASSP (1995)
Masahide Sugiyama, Jin'ichi Murakami, Hideyuki Watanabe
Speech segmentation and clustering problem based on an unknown-multiple N signal source model - an application to segmented speech clustering based on speaker features. Systems and Computers in Japan 25 (9) (1994)
Masahide Sugiyama, Jin'ichi Murakami, Hideyuki Watanabe
Speech segmentation and clustering based on speaker features. ICASSP (2) (1993)
Hideyuki Watanabe, Masakiyo Suzuki, Nobuo Nagai, Nobuhiro Miki
Maximum likelihood bearing estimation by quasi-Newton method using a uniform linear array. ICASSP (1991)