Shigeru Katagiri

104 papers A* 1A 5B 1Misc 27Journal 33Unranked 37

Year	Rank	Type	Title / Venue / Authors
2024	Misc	`conf`	How Does End-To-End Speech Recognition Training Impact Speech Enhancement Artifacts? ICASSP Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri
2024	J	`jnl`	Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance. CoRR Tsubasa Ochiai, Kazuma Iwamoto, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri
2024	J	`jnl`	Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance. IEEE ACM Trans. Audio Speech Lang. Process. Tsubasa Ochiai, Kazuma Iwamoto, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri
2022	—	`conf`	A Proposal of an Improved Maximum Bayes Boundary-Ness Training Method. SPML Koki Kishishita, Shigeru Katagiri, Miho Ohsaki
2022	—	`conf`	An Investigation of Feature Difference Between Child and Adult Voices Using Line Spectral Pairs. SPML Ginji Hayashi, Shigeru Katagiri, Xugang Lu, Miho Ohsaki
2022	J	`jnl`	How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR. CoRR Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri
2022	A	`conf`	How bad are artifacts?: Analyzing the impact of speech enhancement errors on ASR. INTERSPEECH Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri
2021	J	`jnl`	An Improved Boundary Uncertainty-Based Estimation for Classifier Evaluation. J. Signal Process. Syst. David Ha, Shigeru Katagiri, Hideyuki Watanabe, Miho Ohsaki
2021	—	`conf`	Evaluation of the Neural-network-based Method to Discover Sets and Representatives of Nonlinearly Dependent Variables. CYBCONF Miho Ohsaki, Hayato Sasaki, Naoya Kishimoto, Shigeru Katagiri, Kei Ohnishi, Yakub Sebastian, Patrick H. H. Then
2021	J	`jnl`	NNR-GL: A Measure to Detect Co-Nonlinearity Based on Neural Network Regression Regularized by Group Lasso. IEEE Access Miho Ohsaki, Naoya Kishimoto, Hayato Sasaki, Ryoji Ikeura, Shigeru Katagiri, Kei Ohnishi, Yakub Sebastian, Patrick H. H. Then
2020	J	`jnl`	A Practical Method Based on Bayes Boundary-Ness for Optimal Classifier Parameter Status Selection. J. Signal Process. Syst. David Ha, Yuya Tomotoshi, Masahiro Senda, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki
2019	—	`conf`	Maximum Bayes Boundary-Ness Training For Pattern Classification. SPML Masahiro Senda, David Ha, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki
2019	—	`conf`	Minimum Classification Error Training with Speech Synthesis-Based Regularization for Speech Recognition. SPML Naoto Umezaki, Takumi Okubo, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki
2019	—	`conf`	Optimal Classifier Parameter Status Selection Based on Bayes Boundary-ness for Multi-ProtoType and Multi-Layer Perceptron Classifiers. IUKM Yuya Tomotoshi, David Ha, Emilie Delattre, Hideyuki Watanabe, Xugang Lu, Shigeru Katagiri, Miho Ohsaki
2018	—	`conf`	Body Part Diagram Recognition in Medical Records: Application of the Histograms of Oriented Gradients and the Mahalanobis-Distance-Based Classifier. SCIS&ISIS Miho Ohsaki, Hayato Sasaki, Hiroharu Kawanaka, Shigeru Katagiri
2018	—	`conf`	Discovery of Sets and Representatives of Variables in Co-nonlinear Relationships by Neural Network Regression and Group Lasso. BIBM Miho Ohsaki, Hayato Sasaki, Naoya Kishimoto, Shigeru Katagiri, Patrick Hang Hui Then
2018	—	`conf`	Optimal Classifier Model Status Selection using Bayes boundary uncertainty. MLSP David Ha, Emilie Delattre, Yuya Tomotoshi, Masahiro Senda, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki
2018	—	`conf`	Optimality Analysis of Boundary-Uncertainty-Based Classifier Model Parameter Status Selection Method. SPML David Ha, Hideyuki Watanabe, Yuya Tomotoshi, Emilie Delattre, Shigeru Katagiri
2018	Misc	`conf`	Speaker Adaptation for Multichannel End-to-End Speech Recognition. ICASSP Tsubasa Ochiai, Shinji Watanabe, Shigeru Katagiri, Takaaki Hori, John R. Hershey
2017	Misc	`conf`	Automatic node selection for Deep Neural Networks using Group Lasso regularization. ICASSP Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Shigeru Katagiri
2017	—	`conf`	Compact kernel classifiers trained with minimum classification error criterion. MLSP Ryoma Tani, Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki
2017	J	`jnl`	Confusion-Matrix-Based Kernel Logistic Regression for Imbalanced Data Classification. IEEE Trans. Knowl. Data Eng. Miho Ohsaki, Peng Wang, Kenji Matsuda, Shigeru Katagiri, Hideyuki Watanabe, Anca L. Ralescu
2017	Misc	`conf`	Cumulative moving averaged bottleneck speaker vectors for online speaker adaptation of CNN-based acoustic models. ICASSP Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Atsunori Ogawa, Taichi Asami, Shigeru Katagiri, Tomohiro Nakatani
2017	—	`conf`	Does speech enhancement work with end-to-end ASR objectives?: Experimental analysis of multichannel end-to-end ASR. MLSP Tsubasa Ochiai, Shinji Watanabe, Shigeru Katagiri
2016	J	`jnl`	Automatic Node Selection for Deep Neural Networks using Group Lasso Regularization. CoRR Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Shigeru Katagiri
2016	Misc	`conf`	Bottleneck linear transformation network adaptation for speaker adaptive training-based hybrid DNN-HMM speech recognizer. ICASSP Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Hisashi Kawai, Shigeru Katagiri
2016	J	`jnl`	Speaker Adaptive Training Localizing Speaker Modules in DNN for Hybrid DNN-HMM Speech Recognizers. IEICE Trans. Inf. Syst. Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Chiori Hori, Hisashi Kawai, Shigeru Katagiri
2015	B	`conf`	Formulation of the kernel logistic regression based on the confusion matrix. CEC Miho Ohsaki, Kenji Matsuda, Peng Wang, Shigeru Katagiri, Hideyuki Watanabe
2015	Misc	`conf`	Speaker adaptive training for deep neural networks embedding linear transformation networks. ICASSP Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Chiori Hori, Shigeru Katagiri
2014	J	`jnl`	Guest Editorial: Machine Learning for Signal Processing. J. Signal Process. Syst. Shigeru Katagiri, Atsushi Nakamura, Tülay Adali, Jianhua Tao, Jan Larsen, Tieniu Tan
2014	J	`jnl`	Minimum Classification Error Training Incorporating Automatic Loss Smoothness Determination. J. Signal Process. Syst. Hideyuki Watanabe, Jun'ichi Tokuno, Tsukasa Ohashi, Shigeru Katagiri, Miho Ohsaki, Shigeki Matsuda, Hideki Kashioka
2014	J	`jnl`	Robust and Efficient Pattern Classification using Large Geometric Margin Minimum Classification Error Training. J. Signal Process. Syst. Hideyuki Watanabe, Tsukasa Ohashi, Shigeru Katagiri, Miho Ohsaki, Shigeki Matsuda, Hideki Kashioka
2014	Misc	`conf`	Speaker Adaptive Training using Deep Neural Networks. ICASSP Tsubasa Ochiai, Shigeki Matsuda, Xugang Lu, Chiori Hori, Shigeru Katagiri
2012	—	`conf`	Application of kernel logistic regression to the prediction of liver fibrosis stages in chronic hepatitis C. SCIS&ISIS Kenji Matsuda, Miho Ohsaki, Shigeru Katagiri, Hideto Yokoi, Katsuhiko Takabayashi
2012	Misc	`conf`	Increasing virtual samples through loss smoothness determination in large geometric margin minimum classification error training. ICASSP Tsukasa Ohashi, Hideyuki Watanabe, Jun'ichi Tokuno, Shigeru Katagiri, Miho Ohsaki, Shigeki Matsuda, Hideki Kashioka
2012	—	`conf`	Minimum classification error vs. maximum margin: How should we penalize unseen samples? CIP Shigeru Katagiri, Hideyuki Watanabe
2011	—	`conf`	Minimum classification error training with automatic setting of loss smoothness. MLSP Hideyuki Watanabe, Jun'ichi Tokuno, Tsukasa Ohashi, Shigeru Katagiri, Miho Ohsaki
2011	—	`conf`	Minimum classification error training with geometric margin enhancement for robust pattern recognition. MLSP Hideyuki Watanabe, Shigeru Katagiri, Miho Ohsaki
2011	—	`conf`	Preface. MLSP Tieniu Tan, Shigeru Katagiri, Jianhua Tao, Atsushi Nakamura, Jan Larsen
2010	Misc	`conf`	Minimum Error Classification with geometric margin control. ICASSP Hideyuki Watanabe, Shigeru Katagiri, Kouta Yamada, Erik McDermott, Atsushi Nakamura, Shinji Watanabe, Miho Ohsaki
2009	Misc	`conf`	A unified view for discriminative objective functions based on negative exponential of difference measure between strings. ICASSP Atsushi Nakamura, Erik McDermott, Shinji Watanabe, Shigeru Katagiri
2009	A*	`conf`	Analysis of Subsequence Time-Series Clustering Based on Moving Average. ICDM Miho Ohsaki, Masakazu Nakase, Shigeru Katagiri
2007	J	`jnl`	Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error. IEEE Trans. Speech Audio Process. Erik McDermott, Timothy J. Hazen, Jonathan Le Roux, Atsushi Nakamura, Shigeru Katagiri
2007	J	`jnl`	Inverting mappings from smooth paths through R Speech Commun. John Hogden, Philip Rubin, Erik McDermott, Shigeru Katagiri, Louis Goldstein
2006	J	`jnl`	Advanced computational models and learning theories for spoken language processing. IEEE Comput. Intell. Mag. Atsushi Nakamura, Shinji Watanabe, Takaaki Hori, Erik McDermott, Shigeru Katagiri
2006	J	`jnl`	Discriminative training via minimization of risk estimates based on Parzen smoothing. Appl. Intell. Erik McDermott, Shigeru Katagiri
2006	J	`jnl`	Dynamic Assignment of Gaussian Components in Modelling Speech Spectra. J. VLSI Signal Process. Parham Zolfaghari, Hiroko Kato, Yasuhiro Minami, Atsushi Nakamura, Shigeru Katagiri, Roy D. Patterson
2005	—	`conf`	Minimum Classification Error for Large Scale Speech Recognition Tasks using Weighted Finite State Transducers. ICASSP (1) Erik McDermott, Shigeru Katagiri
2004	J	`jnl`	A derivation of minimum classification error from the theoretical classification risk using Parzen estimation. Comput. Speech Lang. Erik McDermott, Shigeru Katagiri
2004	A	`conf`	A theoretical analysis of speech recognition based on feature trajectory models. INTERSPEECH Yasuhiro Minami, Erik McDermott, Atsushi Nakamura, Shigeru Katagiri
2004	—	`conf`	Bayesian modelling of the speech spectrum using mixture of Gaussians. ICASSP (1) Parham Zolfaghari, Shinji Watanabe, Atsushi Nakamura, Shigeru Katagiri
2003	—	`conf`	A new formalization of minimum classification error using a Parzen estimate of classification chance. ICASSP (2) Erik McDermott, Shigeru Katagiri
2003	A	`conf`	Blind inversion of multidimensional functions for speech enhancement. INTERSPEECH John Hogden, Patrick Valdez, Shigeru Katagiri, Erik McDermott
2003	—	`conf`	Deriving disambiguous queries in a spoken interactive ODQA system. ICASSP (1) Chiori Hori, Takaaki Hori, Hideki Isozaki, Eisaku Maeda, Shigeru Katagiri, Sadaoki Furui
2003	—	`conf`	Pervasive unsupervised adaptation for lecture speech transcription. ICASSP (1) Daniel Willett, Thomas Niesler, Erik McDermott, Yasuhiro Minami, Shigeru Katagiri
2003	—	`conf`	Recognition method with parametric trajectory generated from mixture distribution HMMs. ICASSP (1) Yasuhiro Minami, Erik McDermott, Atsushi Nakamura, Shigeru Katagiri
2002	Misc	`conf`	A recognition method with parametric trajectory synthesized using direct relations between static and dynamic feature vector time series. ICASSP Yasuhiro Minami, Erik McDermott, Atsushi Nakamura, Shigeru Katagiri
2002	A	`conf`	Classification error from the theoretical Bayes classification risk. INTERSPEECH Erik McDermott, Shigeru Katagiri
2002	J	`jnl`	Guest editorial special issue on intelligent multimedia processing. IEEE Trans. Neural Networks Ling Guan, Tülay Adali, Shigeru Katagiri, Jan Larsen, José C. Príncipe
2002	—	`conf`	Minimum classification error via a Parzen window based estimate of the theoretical Bayes classification risk. NNSP Erik McDermott, Shigeru Katagiri
2002	Misc	`conf`	Recent advances in efficient decoding combining on-line transducer composition and smoothed language model incorporation. ICASSP Daniel Willett, Shigeru Katagiri
2001	J	`jnl`	A new approach to designing a feature extractor in speaker identification based on discriminative feature extraction. Speech Commun. Chiyomi Miyajima, Hideyuki Watanabe, Keiichi Tokuda, Tadashi Kitamura, Shigeru Katagiri
2001	J	`jnl`	An application of discriminative feature extraction to filter-bank-based speech recognition. IEEE Trans. Speech Audio Process. Alain Biem, Shigeru Katagiri, Erik McDermott, Biing-Hwang Juang
2001	A	`conf`	Time and memory efficient viterbi decoding for LVCSR using a precompiled search network. INTERSPEECH Daniel Willett, Erik McDermott, Yasuhiro Minami, Shigeru Katagiri
2000	Misc	`conf`	Discriminative training for large vocabulary telephone-based name recognition. ICASSP Erik McDermott, Alain Biem, Seiichi Tenpaku, Shigeru Katagiri
2000	—	`conf`	Law discovery from financial data using neural networks. CIFEr Kazumi Saito, Naonori Ueda, Shigeru Katagiri, Yutaka Fukai, Hiroshi Fujimaru, Masayuki Fujinawa
1999	J	`jnl`	A new approach to acoustic signal monitoring based on the generalized probabilistic descent method. IEEE Trans. Signal Process. Hideyuki Watanabe, Yuji Matsumoto, Satoru Tanaka, Shigeru Katagiri
1999	—	`conf`	Speaker recognition based on discriminative feature extraction - optimization of mel-cepstral features using second-order all-pass warping function. EUROSPEECH Chiyomi Miyajima, Hideyuki Watanabe, Tadashi Kitamura, Shigeru Katagiri
1998	Misc	`conf`	Minimum detection error training for acoustic signal monitoring. ICASSP Hideyuki Watanabe, Yuji Matsumoto, Shigeru Katagiri
1998	J	`jnl`	Pattern recognition using a family of design algorithms based upon the generalized probabilistic descent method. Proc. IEEE Shigeru Katagiri, Biing-Hwang Juang, Chin-Hui Lee
1997	Misc	`conf`	Cepstrum-based filter-bank design using discriminative feature extraction training at various levels. ICASSP Alain Biem, Shigeru Katagiri
1997	J	`jnl`	Discriminative metric design for robust pattern recognition. IEEE Trans. Signal Process. Hideyuki Watanabe, Tsuyoshi Yamaguchi, Shigeru Katagiri
1997	Misc	`conf`	Efficient normalization based upon GPD [generalized probabilistic descent]. ICASSP Eric A. Woudenberg, Alain Biem, Erik McDermott, Shigeru Katagiri
1997	J	`jnl`	Guest Editors' Introduction: Neural Networks For Signal Processing. IEEE Trans. Signal Process. Anthony G. Constantinides, Simon Haykin, Yu Hen Hu, Jenq-Neng Hwang, Shigeru Katagiri, Sun-Yuan Kung, Tomaso A. Poggio
1997	Misc	`conf`	HMM speech recognizer based on discriminative metric design. ICASSP Hideyuki Watanabe, Shigeru Katagiri
1997	J	`jnl`	Pattern recognition using discriminative feature extraction. IEEE Trans. Signal Process. Alain Biem, Shigeru Katagiri, Biing-Hwang Juang
1997	—	`conf`	String-level MCE for continuous phoneme recognition. EUROSPEECH Erik McDermott, Shigeru Katagiri
1996	Misc	`conf`	A telephone-based directory assistance system adaptively trained using minimum classification error/generalized probabilistic descent. ICASSP Erik McDermott, Eric A. Woudenberg, Shigeru Katagiri
1995	J	`jnl`	A Minimum Error Approach to Spotting-Based Pattern Recognition. IEICE Trans. Inf. Syst. Takashi Komori, Shigeru Katagiri
1995	—	`conf`	A discriminative filter bank model for speech recognition. EUROSPEECH Alain Biem, Erik McDermott, Shigeru Katagiri
1995	Misc	`conf`	Discriminative metric design for pattern recognition. ICASSP Hideyuki Watanabe, Tsuyoshi Yamaguchi, Shigeru Katagiri
1994	—	`conf`	A novel fuzzy partition model architecture for classifying dynamic patterns. ICSLP Yoshinaga Koto, Shigeru Katagiri
1994	—	`conf`	Filter bank design based on discriminative feature extraction. ICASSP (1) Alain Biem, Shigeru Katagiri
1994	J	`jnl`	Prototype-based minimum classification error/generalized probabilistic descent training for various speech units. Comput. Speech Lang. Erik McDermott, Shigeru Katagiri
1994	J	`jnl`	Prototype-based minimum error training for speech recognition. Appl. Intell. Erik McDermott, Shigeru Katagiri
1993	J	`jnl`	A new hybrid algorithm for speech recognition based on HMM segmentation and learning vector quantization. IEEE Trans. Speech Audio Process. Shigeru Katagiri, Chin-Hui Lee
1993	—	`conf`	An optimal learning method for minimizing spotting errors. ICASSP (2) Takashi Komori, Shigeru Katagiri
1993	—	`conf`	Feature extraction based on minimum classification error/generalized probabilistic descent method. ICASSP (2) Alain Biem, Shigeru Katagiri
1993	—	`conf`	Prototype-based MCE/GPD training for word spotting and connected word recognition. ICASSP (2) Erik McDermott, Shigeru Katagiri
1992	Misc	`conf`	Application of a generalized probabilistic descent method to dynamic time warping-based speech recognition. ICASSP Takashi Komori, Shigeru Katagiri
1992	J	`jnl`	Discriminative learning for minimum error classification [pattern recognition]. IEEE Trans. Signal Process. Biing-Hwang Juang, Shigeru Katagiri
1992	Misc	`conf`	Prototype-based discriminative training for various speech units. ICASSP Erik McDermott, Shigeru Katagiri
1991	Misc	`conf`	A new connected word recognition algorithm based on HMM/LVQ segmentation and LVQ classification. ICASSP Padma Ramesh, Shigeru Katagiri, Chin-Hui Lee
1991	J	`jnl`	LVQ-based shift-tolerant phoneme recognition. IEEE Trans. Signal Process. Erik McDermott, Shigeru Katagiri
1991	Misc	`conf`	Speaker-independent large vocabulary word recognition using an LVQ/HMM hybrid algorithm. ICASSP Hitoshi Iwamida, Shigeru Katagiri, Erik McDermott
1990	Misc	`conf`	A hybrid speech recognition system using HMMs with an LVQ-trained codebook. ICASSP Hitoshi Iwamida, Shigeru Katagiri, Erik McDermott, Yoh'ichi Tohkura
1990	—	`conf`	A large-scale Japanese speech database. ICSLP Yoshinori Sagisaka, Kazuya Takeda, M. Abel, Shigeru Katagiri, T. Umeda, Hisao Kuwabara
1990	J	`jnl`	ATR Japanese speech database as a tool of speech recognition and synthesis. Speech Commun. Akira Kurematsu, Kazuya Takeda, Yoshinori Sagisaka, Shigeru Katagiri, Hisao Kuwabara, Kiyohiro Shikano
1990	—	`conf`	On the robustness of HMM and ANN speech recognition algorithms. ICSLP Yasuhiro Minami, Toshiyuki Hanazawa, Hitoshi Iwamida, Erik McDermott, Kiyohiro Shikano, Shigeru Katagiri, Masaona Kagawa
1989	Misc	`conf`	A new algorithm for representing acoustic feature dynamics. ICASSP Shigeru Katagiri, Erik McDermott, Manami Yokota
1989	Misc	`conf`	Construction of a large-scale Japanese speech database and its management system. ICASSP Hisao Kuwabara, Kazuya Takeda, Yoshinori Sagisaka, Shigeru Katagiri, S. Morikawa, T. Watanabe
1989	Misc	`conf`	Shift-invariant, multi-category phoneme recognition using Kohonen's LVQ2. ICASSP Erik McDermott, Shigeru Katagiri
1987	—	`conf`	Acoustic-phonetic labels in a Japanese speech database. ECST Kazuya Takeda, Yoshinori Sagisaka, Shigeru Katagiri
1987	—	`conf`	Phoneme recognition using visual features on speech spectrograms. ECST Shigeru Katagiri, Manami Yokota