Kenichi Kumatani

PRINCIPAL RESEARCHER

Publications

View by:

- Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model
  
  Haibin Wu, Yuxuan Hu, Ruchao Fan, Xiaofei Wang, Kenichi Kumatani, Bo Ren, Jianwei Yu, Heng Lu, Lijuan Wang, Yao Qian, Jinyu Li
  
  2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) | June 2025, pp. 1-7
  
  DOI Publication Publication
- Knowledge Distillation for Mixture of Experts Models in Speech Recognition
  
  Felipe Cruz Salinas, Kenichi Kumatani, Robert Gmyr, Linquan Liu, Yu Shi
  
  MSR-TR-2022-6 | May 2022
  
  Published by Microsoft
  
  Publication
- Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition
  
  Kenichi Kumatani, Robert Gmyr, Felipe Cruz Salinas, Linquan Liu, Wei Zuo , Devang Patel, Eric Sun, Yu Shi
  
  CoRR | December 2021, Vol abs/2112.05820
  
  Publication
- Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
  
  Tae Jin Park, Kenichi Kumatani, Dimitrios Dimitriadis
  
  October 2021
  
  Publication Project
- One-Shot Voice Conversion with Speaker-Agnostic StarGAN
  
  Sefik Emre Eskimez, Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr
  
  INTERSPEECH 2022 | August 2021
  
  Publication DOI Project
- UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
  
  Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang
  
  2021 International Conference on Machine Learning | July 2021
  
  Publication
- Ensemble Combination between Different Time Segmentations
  
  Jeremy Wong, Dimitrios Dimitriadis, Kenichi Kumatani, Yashesh Gaur, George Polovets, Partha Parthasarathy, Eric Sun, Jinyu Li, Yifan Gong
  
  2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | June 2021
  
  Publication
- Sequence-Level Self-Learning with Multiple Hypotheses
  
  Kenichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur, Robert Gmyr, Sefik Emre Eskimez, Jinyu Li, Michael Zeng
  
  Interspeech | October 2020
  
  Publication DOI Project
- Federated Transfer Learning with Dynamic Gradient Aggregation
  
  Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
  
  August 2020
  
  Publication Project

- Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model
  
  Haibin Wu, Yuxuan Hu, Ruchao Fan, Xiaofei Wang, Kenichi Kumatani, Bo Ren, Jianwei Yu, Heng Lu, Lijuan Wang, Yao Qian, Jinyu Li
  
  2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) | June 2025, pp. 1-7
  
  DOI Publication Publication
- Knowledge Distillation for Mixture of Experts Models in Speech Recognition
  
  Felipe Cruz Salinas, Kenichi Kumatani, Robert Gmyr, Linquan Liu, Yu Shi
  
  MSR-TR-2022-6 | May 2022
  
  Published by Microsoft
  
  Publication
- Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition
  
  Kenichi Kumatani, Robert Gmyr, Felipe Cruz Salinas, Linquan Liu, Wei Zuo , Devang Patel, Eric Sun, Yu Shi
  
  CoRR | December 2021, Vol abs/2112.05820
  
  Publication
- Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
  
  Tae Jin Park, Kenichi Kumatani, Dimitrios Dimitriadis
  
  October 2021
  
  Publication Project
- One-Shot Voice Conversion with Speaker-Agnostic StarGAN
  
  Sefik Emre Eskimez, Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr
  
  INTERSPEECH 2022 | August 2021
  
  Publication DOI Project
- UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
  
  Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang
  
  2021 International Conference on Machine Learning | July 2021
  
  Publication
- Ensemble Combination between Different Time Segmentations
  
  Jeremy Wong, Dimitrios Dimitriadis, Kenichi Kumatani, Yashesh Gaur, George Polovets, Partha Parthasarathy, Eric Sun, Jinyu Li, Yifan Gong
  
  2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | June 2021
  
  Publication
- Sequence-Level Self-Learning with Multiple Hypotheses
  
  Kenichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur, Robert Gmyr, Sefik Emre Eskimez, Jinyu Li, Michael Zeng
  
  Interspeech | October 2020
  
  Publication DOI Project
- Federated Transfer Learning with Dynamic Gradient Aggregation
  
  Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
  
  August 2020
  
  Publication Project
- Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model
  
  Haibin Wu, Yuxuan Hu, Ruchao Fan, Xiaofei Wang, Kenichi Kumatani, Bo Ren, Jianwei Yu, Heng Lu, Lijuan Wang, Yao Qian, Jinyu Li
  
  2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) | June 2025, pp. 1-7
  
  DOI Publication Publication
- Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
  
  Tae Jin Park, Kenichi Kumatani, Dimitrios Dimitriadis
  
  October 2021
  
  Publication Project
- Federated Transfer Learning with Dynamic Gradient Aggregation
  
  Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
  
  August 2020
  
  Publication Project
- UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
  
  Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang
  
  2021 International Conference on Machine Learning | July 2021
  
  Publication
- Ensemble Combination between Different Time Segmentations
  
  Jeremy Wong, Dimitrios Dimitriadis, Kenichi Kumatani, Yashesh Gaur, George Polovets, Partha Parthasarathy, Eric Sun, Jinyu Li, Yifan Gong
  
  2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | June 2021
  
  Publication
- Ensemble Combination between Different Time Segmentations
  
  Jeremy Wong, Dimitrios Dimitriadis, Kenichi Kumatani, Yashesh Gaur, George Polovets, Partha Parthasarathy, Eric Sun, Jinyu Li, Yifan Gong
  
  2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | June 2021
  
  Publication
- Ensemble Combination between Different Time Segmentations
  
  Jeremy Wong, Dimitrios Dimitriadis, Kenichi Kumatani, Yashesh Gaur, George Polovets, Partha Parthasarathy, Eric Sun, Jinyu Li, Yifan Gong
  
  2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | June 2021
  
  Publication
- Federated Transfer Learning with Dynamic Gradient Aggregation
  
  Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
  
  August 2020
  
  Publication Project
- Federated Transfer Learning with Dynamic Gradient Aggregation
  
  Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
  
  August 2020
  
  Publication Project

- Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model
  
  Haibin Wu, Yuxuan Hu, Ruchao Fan, Xiaofei Wang, Kenichi Kumatani, Bo Ren, Jianwei Yu, Heng Lu, Lijuan Wang, Yao Qian, Jinyu Li
  
  2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) | June 2025, pp. 1-7
  
  DOI Publication Publication
- Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition
  
  Kenichi Kumatani, Robert Gmyr, Felipe Cruz Salinas, Linquan Liu, Wei Zuo , Devang Patel, Eric Sun, Yu Shi
  
  CoRR | December 2021, Vol abs/2112.05820
  
  Publication
- One-Shot Voice Conversion with Speaker-Agnostic StarGAN
  
  Sefik Emre Eskimez, Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr
  
  INTERSPEECH 2022 | August 2021
  
  Publication DOI Project
- UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
  
  Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang
  
  2021 International Conference on Machine Learning | July 2021
  
  Publication
- Ensemble Combination between Different Time Segmentations
  
  Jeremy Wong, Dimitrios Dimitriadis, Kenichi Kumatani, Yashesh Gaur, George Polovets, Partha Parthasarathy, Eric Sun, Jinyu Li, Yifan Gong
  
  2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | June 2021
  
  Publication
- Sequence-Level Self-Learning with Multiple Hypotheses
  
  Kenichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur, Robert Gmyr, Sefik Emre Eskimez, Jinyu Li, Michael Zeng
  
  Interspeech | October 2020
  
  Publication DOI Project
- Knowledge Distillation for Mixture of Experts Models in Speech Recognition
  
  Felipe Cruz Salinas, Kenichi Kumatani, Robert Gmyr, Linquan Liu, Yu Shi
  
  MSR-TR-2022-6 | May 2022
  
  Published by Microsoft
  
  Publication
- Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
  
  Tae Jin Park, Kenichi Kumatani, Dimitrios Dimitriadis
  
  October 2021
  
  Publication Project
- Federated Transfer Learning with Dynamic Gradient Aggregation
  
  Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez
  
  August 2020
  
  Publication Project

Kenichi Kumatani

Publications

Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model

Knowledge Distillation for Mixture of Experts Models in Speech Recognition

Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition

Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal

One-Shot Voice Conversion with Speaker-Agnostic StarGAN

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

Ensemble Combination between Different Time Segmentations

Sequence-Level Self-Learning with Multiple Hypotheses

Federated Transfer Learning with Dynamic Gradient Aggregation

Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model

Knowledge Distillation for Mixture of Experts Models in Speech Recognition

Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition

Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal

One-Shot Voice Conversion with Speaker-Agnostic StarGAN

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

Ensemble Combination between Different Time Segmentations

Sequence-Level Self-Learning with Multiple Hypotheses

Federated Transfer Learning with Dynamic Gradient Aggregation

Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model

Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal

Federated Transfer Learning with Dynamic Gradient Aggregation

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

Ensemble Combination between Different Time Segmentations

Ensemble Combination between Different Time Segmentations

Ensemble Combination between Different Time Segmentations

Federated Transfer Learning with Dynamic Gradient Aggregation

Federated Transfer Learning with Dynamic Gradient Aggregation

Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model

Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition

One-Shot Voice Conversion with Speaker-Agnostic StarGAN

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

Ensemble Combination between Different Time Segmentations

Sequence-Level Self-Learning with Multiple Hypotheses

Knowledge Distillation for Mixture of Experts Models in Speech Recognition

Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal

Federated Transfer Learning with Dynamic Gradient Aggregation