Ken'ichi Kumatani

56 papers A* 1A 9B 1C 4Misc 12Journal 16Unranked 11

Year	Rank	Type	Title / Venue / Authors
2025	C	`conf`	Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model. ASRU Haibin Wu, Yuxuan Hu, Ruchao Fan, Xiaofei Wang, Ken'ichi Kumatani, Bo Ren, Jianwei Yu, Heng Lu, Lijuan Wang, Yao Qian, Jinyu Li
2022	J	`jnl`	Deploying self-supervised learning in the wild for hybrid automatic speech recognition. CoRR Mostafa Karimi, Changliang Liu, Ken'ichi Kumatani, Yao Qian, Tianyu Wu, Jian Wu
2021	J	`jnl`	Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition. CoRR Ken'ichi Kumatani, Robert Gmyr, Felipe Cruz-Salinas, Linquan Liu, Wei Zuo, Devang Patel, Eric Sun, Yu Shi
2021	J	`jnl`	Dynamic Gradient Aggregation for Federated Domain Adaptation. CoRR Dimitrios Dimitriadis, Ken'ichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
2021	Misc	`conf`	Ensemble Combination between Different Time Segmentations. ICASSP Jeremy Heng Meng Wong, Dimitrios Dimitriadis, Ken'ichi Kumatani, Yashesh Gaur, George Polovets, Partha Parthasarathy, Eric Sun, Jinyu Li, Yifan Gong
2021	J	`jnl`	Multilingual Speech Recognition using Knowledge Transfer across Learning Processes. CoRR Rimita Lahiri, Ken'ichi Kumatani, Eric Sun, Yao Qian
2021	A	`conf`	One-Shot Voice Conversion with Speaker-Agnostic StarGAN. Interspeech Sefik Emre Eskimez, Dimitrios Dimitriadis, Ken'ichi Kumatani, Robert Gmyr
2021	J	`jnl`	Sequence-level self-learning with multiple hypotheses. CoRR Ken'ichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur, Robert Gmyr, Sefik Emre Eskimez, Jinyu Li, Michael Zeng
2021	J	`jnl`	Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal. CoRR Tae Jin Park, Ken'ichi Kumatani, Dimitrios Dimitriadis
2021	A*	`conf`	UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data. ICML Chengyi Wang, Yu Wu, Yao Qian, Ken'ichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang
2021	J	`jnl`	UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data. CoRR Chengyi Wang, Yu Wu, Yao Qian, Ken'ichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang
2020	A	`conf`	A Federated Approach in Training Acoustic Models. INTERSPEECH Dimitrios Dimitriadis, Ken'ichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
2020	J	`jnl`	Federated Transfer Learning with Dynamic Gradient Aggregation. CoRR Dimitrios Dimitriadis, Ken'ichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
2020	Misc	`conf`	Fully Learnable Front-End for Multi-Channel Acoustic Modeling Using Semi-Supervised Learning. ICASSP Sanna Wager, Aparna Khare, Minhua Wu, Ken'ichi Kumatani, Shiva Sundaram
2020	J	`jnl`	Fully Learnable Front-End for Multi-Channel Acoustic Modeling using Semi-Supervised Learning. CoRR Sanna Wager, Aparna Khare, Minhua Wu, Ken'ichi Kumatani, Shiva Sundaram
2020	Misc	`conf`	Robust Multi-Channel Speech Recognition Using Frequency Aligned Network. ICASSP Taejin Park, Ken'ichi Kumatani, Minhua Wu, Shiva Sundaram
2020	J	`jnl`	Robust Multi-channel Speech Recognition using Frequency Aligned Network. CoRR Taejin Park, Ken'ichi Kumatani, Minhua Wu, Shiva Sundaram
2020	A	`conf`	Sequence-Level Self-Learning with Multiple Hypotheses. INTERSPEECH Ken'ichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur, Robert Gmyr, Sefik Emre Eskimez, Jinyu Li, Michael Zeng
2019	Misc	`conf`	Frequency Domain Multi-channel Acoustic Modeling for Distant Speech Recognition. ICASSP Minhua Wu, Ken'ichi Kumatani, Shiva Sundaram, Nikko Ström, Björn Hoffmeister
2019	J	`jnl`	Frequency Domain Multi-channel Acoustic Modeling for Distant Speech Recognition. CoRR Minhua Wu, Ken'ichi Kumatani, Shiva Sundaram, Nikko Strom, Björn Hoffmeister
2019	Misc	`conf`	Improving Noise Robustness of Automatic Speech Recognition via Parallel Data and Teacher-student Learning. ICASSP Ladislav Mosner, Minhua Wu, Anirudh Raju, Sree Hari Krishnan Parthasarathi, Ken'ichi Kumatani, Shiva Sundaram, Roland Maas, Björn Hoffmeister
2019	J	`jnl`	Improving noise robustness of automatic speech recognition via parallel data and teacher-student learning. CoRR Ladislav Mosner, Minhua Wu, Anirudh Raju, Sree Hari Krishnan Parthasarathi, Ken'ichi Kumatani, Shiva Sundaram, Roland Maas, Björn Hoffmeister
2019	J	`jnl`	Multi-Geometry Spatial Acoustic Modeling for Distant Speech Recognition. CoRR Ken'ichi Kumatani, Minhua Wu, Shiva Sundaram, Nikko Strom, Björn Hoffmeister
2019	Misc	`conf`	Multi-geometry Spatial Acoustic Modeling for Distant Speech Recognition. ICASSP Ken'ichi Kumatani, Minhua Wu, Shiva Sundaram, Nikko Ström, Björn Hoffmeister
2018	Misc	`conf`	Time-Delayed Bottleneck Highway Networks Using a DFT Feature for Keyword Spotting. ICASSP Jinxi Guo, Ken'ichi Kumatani, Ming Sun, Minhua Wu, Anirudh Raju, Nikko Strom, Arindam Mandal
2017	C	`conf`	Direct modeling of raw audio with DNNS for wake word detection. ASRU Ken'ichi Kumatani, Sankaran Panchapagesan, Minhua Wu, Minjae Kim, Nikko Strom, Gautam Tiwari, Arindam Mandal
2015	Misc	`conf`	Free energy for speech recognition. ICASSP Rita Singh, Ken'ichi Kumatani
2013	Misc	`conf`	Joint constrained maximum likelihood regression for overlapping speech recognition. ICASSP Ken'ichi Kumatani, Rita Singh, Friedrich Faubel, John W. McDonough, Youssef Oualil
2013	Misc	`conf`	Speaker tracking with spherical microphone arrays. ICASSP John W. McDonough, Ken'ichi Kumatani, Takayuki Arakawa, Kazumasa Yamamoto, Bhiksha Raj
2012	A	`conf`	A signal-separation-based array postfilter for distant speech recognition. INTERSPEECH Rita Singh, Ken'ichi Kumatani, John W. McDonough, Chen Liu
2012	A	`conf`	Microphone Array Post-filter based on Spatially-Correlated Noise Measurements for Distant Speech Recognition. INTERSPEECH Ken'ichi Kumatani, Bhiksha Raj, Rita Singh, John W. McDonough
2012	J	`jnl`	Microphone Array Processing for Distant Speech Recognition: From Close-Talking Microphones to Far-Field Sensors. IEEE Signal Process. Mag. Ken'ichi Kumatani, John W. McDonough, Bhiksha Raj
2012	—	`ch.`	Microphone Arrays. Techniques for Noise Robustness in Automatic Speech Recognition John W. McDonough, Ken'ichi Kumatani
2012	—	`conf`	Microphone array processing for distant speech recognition: Spherical arrays. APSIPA John W. McDonough, Ken'ichi Kumatani, Bhiksha Raj
2012	—	`conf`	Microphone array processing for distant speech recognition: Towards real-world deployment. APSIPA Ken'ichi Kumatani, Takayuki Arakawa, Kazumasa Yamamoto, John W. McDonough, Bhiksha Raj, Rita Singh, Ivan Tashev
2011	—	`conf`	An information filter for voice prompt suppression. ACSCC John W. McDonough, Wei Chu, Ken'ichi Kumatani, Bhiksha Raj, Jill Fain Lehman
2011	—	`conf`	Block-wise incremental adaptation algorithm for maximum kurtosis beamforming. WASPAA Ken'ichi Kumatani, John W. McDonough, Bhiksha Raj
2011	C	`conf`	Maximum kurtosis beamforming with a subspace filter for distant speech recognition. ASRU Ken'ichi Kumatani, John W. McDonough, Bhiksha Raj
2011	—	`conf`	On the combination of voice prompt suppression with maximum kurtosis beamforming. WASPAA John W. McDonough, Bhiksha Raj, Ken'ichi Kumatani
2010	—	`conf`	Maximum negentropy beamforming with superdirectivity. EUSIPCO Ken'ichi Kumatani, Liang Lu, John W. McDonough, Arnab Ghoshal, Dietrich Klakow
2010	—	`—`	Subband beamforming with higher order statistics for distant speech recognition. Ken'ichi Kumatani
2009	J	`jnl`	Beamforming With a Maximum Negentropy Criterion. IEEE Trans. Speech Audio Process. Ken'ichi Kumatani, John W. McDonough, Barbara Rauch, Dietrich Klakow, Philip N. Garner, Weifeng Li
2008	—	`conf`	A Neural Network Based Regression Approach for Recognizing Simultaneous Speech. MLMI Weifeng Li, Ken'ichi Kumatani, John Dines, Mathew Magimai-Doss, Hervé Bourlard
2008	Misc	`conf`	Filter bank design based on minimization of individual aliasing terms for minimum mutual information subband adaptive beamforming. ICASSP Ken'ichi Kumatani, John W. McDonough, S. Schachl, Dietrich Klakow, Philip N. Garner, Weifeng Li
2008	A	`conf`	Maximum kurtosis beamforming with the generalized sidelobe canceller. INTERSPEECH Ken'ichi Kumatani, John W. McDonough, Barbara Rauch, Philip N. Garner, Weifeng Li, John Dines
2007	J	`jnl`	Adaptive Beamforming With a Minimum Mutual Information Criterion. IEEE Trans. Speech Audio Process. Ken'ichi Kumatani, Tobias Gehrig, Uwe Mayer, Emilian Stoimenov, John W. McDonough, Matthias Wölfel
2007	C	`conf`	Minimum mutual information beamforming for simultaneous active speakers. ASRU Ken'ichi Kumatani, Uwe Mayer, Tobias Gehrig, Emilian Stoimenov, John W. McDonough, Matthias Wölfel
2007	—	`conf`	State Synchronous Modeling on Phone Boundary for Audio Visual Speech Recognition and Application to Muti-View Face Images. ICASSP (4) Ken'ichi Kumatani, Rainer Stiefelhagen
2007	—	`conf`	To Separate Speech. MLMI John W. McDonough, Ken'ichi Kumatani, Tobias Gehrig, Emilian Stoimenov, Uwe Mayer, Stefan Schacht, Matthias Wölfel, Dietrich Klakow
2006	A	`conf`	Advances in lecture recognition: the ISL RT-06s evaluation system. INTERSPEECH Christian Fügen, Matthias Wölfel, John W. McDonough, Shajith Ikbal, Florian Kraft, Kornel Laskowski, Mari Ostendorf, Sebastian Stüker, Ken'ichi Kumatani
2006	—	`conf`	Mouth Region Localization Method Based on Gaussian Mixture Model. IWICPAS Ken'ichi Kumatani, Rainer Stiefelhagen
2006	—	`conf`	The ISL RT-06S Speech-to-Text System. MLMI Christian Fügen, Shajith Ikbal, Florian Kraft, Ken'ichi Kumatani, Kornel Laskowski, John W. McDonough, Mari Ostendorf, Sebastian Stüker, Matthias Wölfel
2002	B	`conf`	Multi-Modal Temporal Asynchronicity Modeling by Product HMMs for Robust. ICMI Satoshi Nakamura, Ken'ichi Kumatani, Satoshi Tamura
2002	Misc	`conf`	Robust bi-modal speech recognition based on state synchronous modeling and stream weight optimization. ICASSP Satoshi Nakamura, Ken'ichi Kumatani, Satoshi Tamura
2001	A	`conf`	An Adaptive Integration Based On Product Hmm For Audio-Visual Speech Recognition. ICME Ken'ichi Kumatani, Satoshi Nakamura, Kiyohiro Shikano
2001	A	`conf`	Speech Detection By Facial Image For Multimodal Speech Recognition. ICME Kazumasa Murai, Ken'ichi Kumatani, Satoshi Nakamura