Hideyuki Watanabe

According to our database, Hideyuki Watanabe authored at least 37 papers between 1991 and 2021.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2021

An Improved Boundary Uncertainty-Based Estimation for Classifier Evaluation.

David Ha, Shigeru Katagiri, Hideyuki Watanabe, Miho Ohsaki

J. Signal Process. Syst., 2021

2020

A Practical Method Based on Bayes Boundary-Ness for Optimal Classifier Parameter Status Selection.

David Ha, Yuya Tomotoshi, Masahiro Senda, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki

J. Signal Process. Syst., 2020

2019

Minimum Classification Error Training with Speech Synthesis-Based Regularization for Speech Recognition.

Naoto Umezaki, Takumi Okubo, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki

Proceedings of the 2nd International Conference on Signal Processing and Machine Learning, 2019

Maximum Bayes Boundary-Ness Training For Pattern Classification.

Masahiro Senda, David Ha, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki

Proceedings of the 2nd International Conference on Signal Processing and Machine Learning, 2019

Optimal Classifier Parameter Status Selection Based on Bayes Boundary-ness for Multi-ProtoType and Multi-Layer Perceptron Classifiers.

Yuya Tomotoshi, David Ha, Emilie Delattre, Hideyuki Watanabe, Xugang Lu, Shigeru Katagiri, Miho Ohsaki

Proceedings of the Integrated Uncertainty in Knowledge Modelling and Decision Making, 2019

2018

Optimality Analysis of Boundary-Uncertainty-Based Classifier Model Parameter Status Selection Method.

David Ha, Hideyuki Watanabe, Yuya Tomotoshi, Emilie Delattre, Shigeru Katagiri

Proceedings of the 2018 International Conference on Signal Processing and Machine Learning, 2018

Optimal Classifier Model Status Selection using Bayes boundary uncertainty.

David Ha, Emilie Delattre, Yuya Tomotoshi, Masahiro Senda, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki

Proceedings of the 28th IEEE International Workshop on Machine Learning for Signal Processing, 2018

2017

Confusion-Matrix-Based Kernel Logistic Regression for Imbalanced Data Classification.

Miho Ohsaki, Peng Wang, Kenji Matsuda, Shigeru Katagiri, Hideyuki Watanabe, Anca L. Ralescu

IEEE Trans. Knowl. Data Eng., 2017

Compact kernel classifiers trained with minimum classification error criterion.

Ryoma Tani, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki

Proceedings of the 27th IEEE International Workshop on Machine Learning for Signal Processing, 2017

Automatic node selection for Deep Neural Networks using Group Lasso regularization.

Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Shigeru Katagiri

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016

Speaker Adaptive Training Localizing Speaker Modules in DNN for Hybrid DNN-HMM Speech Recognizers.

Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Chiori Hori, Hisashi Kawai, Shigeru Katagiri

IEICE Trans. Inf. Syst., 2016

Bottleneck linear transformation network adaptation for speaker adaptive training-based hybrid DNN-HMM speech recognizer.

Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Hisashi Kawai, Shigeru Katagiri

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

Speaker adaptive training for deep neural networks embedding linear transformation networks.

Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Chiori Hori, Shigeru Katagiri

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Formulation of the kernel logistic regression based on the confusion matrix.

Miho Ohsaki, Kenji Matsuda, Peng Wang, Shigeru Katagiri, Hideyuki Watanabe

Proceedings of the IEEE Congress on Evolutionary Computation, 2015

2014

Minimum Classification Error Training Incorporating Automatic Loss Smoothness Determination.

Hideyuki Watanabe, Jun'ichi Tokuno, Tsukasa Ohashi, Shigeru Katagiri, Miho Ohsaki, Shigeki Matsuda, Hideki Kashioka

J. Signal Process. Syst., 2014

Robust and Efficient Pattern Classification using Large Geometric Margin Minimum Classification Error Training.

Hideyuki Watanabe, Tsukasa Ohashi, Shigeru Katagiri, Miho Ohsaki, Shigeki Matsuda, Hideki Kashioka

J. Signal Process. Syst., 2014

2012

Increasing virtual samples through loss smoothness determination in large geometric margin minimum classification error training.

Tsukasa Ohashi, Hideyuki Watanabe, Jun'ichi Tokuno, Shigeru Katagiri, Miho Ohsaki, Shigeki Matsuda, Hideki Kashioka

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Minimum classification error vs. maximum margin: How should we penalize unseen samples?

Shigeru Katagiri, Hideyuki Watanabe

Proceedings of the 3rd International Workshop on Cognitive Information Processing, 2012

2011

Minimum classification error training with automatic setting of loss smoothness.

Hideyuki Watanabe, Jun'ichi Tokuno, Tsukasa Ohashi, Shigeru Katagiri, Miho Ohsaki

Proceedings of the 2011 IEEE International Workshop on Machine Learning for Signal Processing, 2011

Minimum classification error training with geometric margin enhancement for robust pattern recognition.

Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki

Proceedings of the 2011 IEEE International Workshop on Machine Learning for Signal Processing, 2011

2010

Minimum Error Classification with geometric margin control.

Hideyuki Watanabe, Shigeru Katagiri, Kouta Yamada, Erik McDermott, Atsushi Nakamura, Shinji Watanabe, Miho Ohsaki

Proceedings of the IEEE International Conference on Acoustics, 2010

2004

Computer-aided diagnosis for distinction between benign and malignant pulmonary nodules on chest radiographs using temporal subtraction images.

Nobuhiro Oda, Shoji Kido, Shoko Yamada, Takatoshi Aoki, Hideyuki Watanabe, Yukunori Korogi, Shigehiko Katsuragawa, Kunio Doi

Proceedings of the CARS 2004. Computer Assisted Radiology and Surgery. Proceedings of the 18th International Congress and Exhibition, 2004

2001

A new approach to designing a feature extractor in speaker identification based on discriminative feature extraction.

Chiyomi Miyajima, Hideyuki Watanabe, Keiichi Tokuda, Tadashi Kitamura, Shigeru Katagiri

Speech Commun., 2001

1999

A new approach to acoustic signal monitoring based on the generalized probabilistic descent method.

Hideyuki Watanabe, Yuji Matsumoto, Satoru Tanaka, Shigeru Katagiri

IEEE Trans. Signal Process., 1999

Speaker recognition based on discriminative feature extraction - optimization of mel-cepstral features using second-order all-pass warping function.

Chiyomi Miyajima, Hideyuki Watanabe, Tadashi Kitamura, Shigeru Katagiri

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

1998

Clinical evaluation of irreversible data compression for computed radiography of the hand.

Kazuhiko Uchida, Hideyuki Watanabe, Takatoshi Aoki, Katsumi Nakamura, Hajime Nakata

J. Digit. Imaging, 1998

Clinical evaluation of irreversible data compression for computed radiography of the chest.

Kanji Egashira, Hajime Nakata, Hideyuki Watanabe, Kazuhiko Uchida, Katsumi Nakamura, Yoichi Ishino, Kenji Horino, Rie Yoshikawa

J. Digit. Imaging, 1998

Minimum detection error training for acoustic signal monitoring.

Hideyuki Watanabe, Yuji Matsumoto, Shigeru Katagiri

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

1997

Discriminative metric design for robust pattern recognition.

Hideyuki Watanabe, Tsuyoshi Yamaguchi, Shigeru Katagiri

IEEE Trans. Signal Process., 1997

HMM speech recognizer based on discriminative metric design.

Hideyuki Watanabe, Shigeru Katagiri

Proceedings of the 1997 IEEE International Conference on Acoustics, 1997

1996

Study of unknown-multiple signal-source clustering problem using ergodic HMM.

Jin'ichi Murakami, Hideyuki Watanabe, Masahide Sugiyama

Syst. Comput. Jpn., 1996

Clinical evaluation of irreversible data compression for computed radiography in excretory urography.

Kazuhiko Uchida, Katsumi Nakamura, Hideyuki Watanabe, Kanji Egashira, Yoichi Ishino, Minoru Murakami, Hajime Nakata

J. Digit. Imaging, 1996

Unknown-multiple signal source clustering problem using ergodic HMM and applied to speaker classification.

Jin'ichi Murakami, Masahide Sugiyama, Hideyuki Watanabe

Proceedings of the 4th International Conference on Spoken Language Processing, 1996

1995

Discriminative metric design for pattern recognition.

Hideyuki Watanabe, Tsuyoshi Yamaguchi, Shigeru Katagiri

Proceedings of the 1995 International Conference on Acoustics, 1995

1994

Speech segmentation and clustering problem based on an unknown-multiple N signal source model - an application to segmented speech clustering based on speaker features.

Masahide Sugiyama, Jin'ichi Murakami, Hideyuki Watanabe

Syst. Comput. Jpn., 1994

1993

Speech segmentation and clustering based on speaker features.

Masahide Sugiyama, Jin'ichi Murakami, Hideyuki Watanabe

Proceedings of the IEEE International Conference on Acoustics, 1993

1991

Maximum likelihood bearing estimation by quasi-Newton method using a uniform linear array.

Hideyuki Watanabe, Masakiyo Suzuki, Nobuo Nagai, Nobuhiro Miki

Proceedings of the 1991 International Conference on Acoustics, 1991