渡邉 紳二

教諭

  • Teacher (Affiliated Senior High School) 教諭, 高等学院
  • 3367 引用
  • 30 h指数
19992019
Pureに変更を加えた場合、すぐここに表示されます。

研究成果 1999 2019

2019
3 引用 (Scopus)

Acoustic Modeling for Distant Multi-talker Speech Recognition with Single- and Multi-channel Branches

Kanda, N., Fujita, Y., Horiguchi, S., Ikeshita, R., Nagamatsu, K. & Watanabe, S., 2019 5 1, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 6630-6634 5 p. 8682273. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2019-May).

研究成果: Conference contribution

Speech recognition
Acoustics
Speech enhancement
Pipelines

Acoustic Modeling for Overlapping Speech Recognition: Jhu Chime-5 Challenge System

Manohar, V., Chen, S. J., Wang, Z., Fujita, Y., Watanabe, S. & Khudanpur, S., 2019 5 1, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 6665-6669 5 p. 8682556. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2019-May).

研究成果: Conference contribution

Speech recognition
Acoustics
Microphones
Beamforming
Network architecture
5 引用 (Scopus)

Back-Translation-Style Data Augmentation for end-to-end ASR

Hayashi, T., Watanabe, S., Zhang, Y., Toda, T., Hori, T., Astudillo, R. & Takeda, K., 2019 2 11, 2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 426-433 8 p. 8639619. (2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings).

研究成果: Conference contribution

Acoustics
acoustics
Speech recognition
Sampling
Costs
2 引用 (Scopus)

Cycle-consistency Training for End-to-end Speech Recognition

Hori, T., Astudillo, R., Hayashi, T., Zhang, Y., Watanabe, S. & Le Roux, J., 2019 5 1, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 6271-6275 5 p. 8683307. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2019-May).

研究成果: Conference contribution

Speech recognition
Transcription
Glossaries
3 引用 (Scopus)

End-to-end Monaural Multi-speaker ASR System without Pretraining

Chang, X., Qian, Y., Yu, K. & Watanabe, S., 2019 5 1, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 6256-6260 5 p. 8682822. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2019-May).

研究成果: Conference contribution

Speech recognition
Labels
Sampling
Experiments
3 引用 (Scopus)

End-to-end Speech Recognition with Word-Based Rnn Language Models

Hori, T., Cho, J. & Watanabe, S., 2019 2 11, 2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 389-396 8 p. 8639693. (2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings).

研究成果: Conference contribution

Speech recognition
language
Decoding
vocabulary
Data storage equipment

Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling

Xu, H., DIng, S. & Watanabe, S., 2019 5 1, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 7110-7114 5 p. 8682494. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2019-May).

研究成果: Conference contribution

Speech recognition
Experiments

Introduction to the Issue on Far-Field Speech Processing in the Era of Deep Learning: Speech Enhancement, Separation, and Recognition

Watanabe, S., Araki, S., Bacchiani, M., Haeb-Umbach, R. & Seltzer, M. L., 2019 8 1, : : IEEE Journal on Selected Topics in Signal Processing. 13, 4, p. 785-786 2 p., 8771260.

研究成果: Editorial

Speech enhancement
Speech processing
Deep learning

Joint Acoustic and Class Inference for Weakly Supervised Sound Event Detection

Kothinti, S., Imoto, K., Chakrabarty, D., Sell, G., Watanabe, S. & Elhilali, M., 2019 5 1, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 36-40 5 p. 8682772. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2019-May).

研究成果: Conference contribution

Labels
Acoustics
Acoustic waves
Acoustic properties
Deep neural networks

Language Model Integration Based on Memory Control for Sequence to Sequence Speech Recognition

Cho, J., Watanabe, S., Hori, T., Baskar, M. K., Inaguma, H., Villalba, J. & Dehak, N., 2019 5 1, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 6191-6195 5 p. 8683380. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2019-May).

研究成果: Conference contribution

Speech recognition
Data storage equipment
Fusion reactions
Decoding
Labels

Low-Resource Contextual Topic Identification on Speech

Liu, C., Wiesner, M., Watanabe, S., Harman, C., Trmal, J., Dehak, N. & Khudanpur, S., 2019 2 11, 2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 656-663 8 p. 8639544. (2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings).

研究成果: Conference contribution

resources
language
acoustics
English language
Acoustics
2 引用 (Scopus)

Multilingual Sequence-to-Sequence Speech Recognition: Architecture, Transfer Learning, and Language Modeling

Cho, J., Baskar, M. K., Li, R., Wiesner, M., Mallidi, S. H., Yalta, N., Karafiat, M., Watanabe, S. & Hori, T., 2019 2 11, 2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 521-527 7 p. 8639655. (2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings).

研究成果: Conference contribution

Speech recognition
language
learning
Recurrent neural networks
neural network
2 引用 (Scopus)

Phasebook and friends: Leveraging discrete representations for source separation

Le Roux, J., Wichern, G., Watanabe, S., Sarroff, A. & Hershey, J. R., 2019 5 1, : : IEEE Journal on Selected Topics in Signal Processing. 13, 2, p. 370-382 13 p., 8664086.

研究成果: Article

Source separation
Masks
Speech enhancement
Ceilings
Chemical activation

Promising Accurate Prefix Boosting for Sequence-to-sequence ASR

Baskar, M. K., Burget, L., Watanabe, S., Karafiat, M., Hori, T. & Cernocky, J. H., 2019 5 1, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 5646-5650 5 p. 8682782. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2019-May).

研究成果: Conference contribution

Testing

Semi-supervised End-to-end Speech Recognition Using Text-to-speech and Autoencoders

Karita, S., Watanabe, S., Iwata, T., Delcroix, M., Ogawa, A. & Nakatani, T., 2019 5 1, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 6166-6170 5 p. 8682890. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2019-May).

研究成果: Conference contribution

Speech recognition
1 引用 (Scopus)

Stream Attention-based Multi-array End-to-end Speech Recognition

Wang, X., Li, R., Mallidi, S. H., Hori, T., Watanabe, S. & Hermansky, H., 2019 5 1, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 7105-7109 5 p. 8682650. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2019-May).

研究成果: Conference contribution

Microphones
Speech recognition
Experiments

The Phasebook: Building Complex Masks via Discrete Representations for Source Separation

Roux, J. L., Wichern, G., Watanabe, S., Sarroff, A. & Hershey, J. R., 2019 5 1, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 66-70 5 p. 8682587. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2019-May).

研究成果: Conference contribution

Source separation
Masks
Speech enhancement
Ceilings

Transfer Learning of Language-independent End-to-end ASR with Language Model Fusion

Inaguma, H., Cho, J., Baskar, M. K., Kawahara, T. & Watanabe, S., 2019 5 1, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 6096-6100 5 p. 8682918. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2019-May).

研究成果: Conference contribution

Fusion reactions
Hybrid systems
Linguistics
Seed

Weakly-Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation

Yalta, N., Watanabe, S., Nakadai, K. & Ogata, T., 2019 7, 2019 International Joint Conference on Neural Networks, IJCNN 2019. Institute of Electrical and Electronics Engineers Inc., 8851872. (Proceedings of the International Joint Conference on Neural Networks; 巻数 2019-July).

研究成果: Conference contribution

Recurrent neural networks
Entropy
Computer graphics
Power spectrum
Cost functions
2018
8 引用 (Scopus)

An End-to-End Language-Tracking Speech Recognizer for Mixed-Language Speech

Seki, H., Watanabe, S., Hori, T., Roux, J. L. & Hershey, J. R., 2018 9 10, 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 巻 2018-April. p. 4919-4923 5 p. 8462180

研究成果: Conference contribution

Speech recognition
Network architecture
Neural networks
Glossaries
Linguistics
9 引用 (Scopus)

A purely end-to-end system for multi-speaker speech recognition

Seki, H., Hori, T., Watanabe, S., Le Roux, J. & Hershey, J. R., 2018 1 1, ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL), p. 2620-2630 11 p. (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); 巻数 1).

研究成果: Conference contribution

Speech recognition
Labels
Source separation
6 引用 (Scopus)

Auxiliary feature based adaptation of end-to-end ASR systems

Delcroix, M., Watanabe, S., Ogawa, A., Karita, S. & Nakatani, T., 2018 1 1, : : Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2018-September, p. 2444-2448 5 p.

研究成果: Conference article

Automatic Speech Recognition
Speech recognition
Neural Networks
Model
Pipelines
4 引用 (Scopus)
Speech Enhancement
Speech enhancement
Speech Recognition
Speech recognition
Speech intelligibility
20 引用 (Scopus)

Diarization is hard: Some experiences and lessons learned for the JHU team in the inaugural dihard challenge

Sell, G., Snyder, D., McCree, A., Garcia-Romero, D., Villalba, J., Maciejewski, M., Manohar, V., Dehak, N., Povey, D., Watanabe, S. & Khudanpur, S., 2018 1 1, : : Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2018-September, p. 2808-2812 5 p.

研究成果: Conference article

Microphones
Performance Measurement
Feature Extraction
Lens
Overlapping

Effectiveness of single-channel BLSTM enhancement for language identification

Frederiksen, P. S., Villalba, J., Watanabe, S., Tan, Z. H. & Dehak, N., 2018 1 1, : : Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2018-September, p. 1823-1827 5 p.

研究成果: Conference article

Language Identification
Memory Term
Enhancement
Telephone
Speech Enhancement
11 引用 (Scopus)

End-to-End Multi-Speaker Speech Recognition

Settle, S., Roux, J. L., Hori, T., Watanabe, S. & Hershey, J. R., 2018 9 10, 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 巻 2018-April. p. 4819-4823 5 p. 8461893

研究成果: Conference contribution

Speech recognition
Transcription
Learning systems
51 引用 (Scopus)

ESPNet: End-to-end speech processing toolkit

Watanabe, S., Hori, T., Karita, S., Hayashi, T., Nishitoba, J., Unno, Y., Soplin, N. E. Y., Heymann, J., Wiesner, M., Chen, N., Renduchintala, A. & Ochiai, T., 2018 1 1, : : Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2018-September, p. 2207-2211 5 p.

研究成果: Conference article

Speech Processing
Speech processing
Automatic Speech Recognition
Speech recognition
Open Source
1 引用 (Scopus)
Evolution Strategies
speech recognition
Speech Recognition
System Development
automation
21 引用 (Scopus)

Language independent end-to-end architecture for joint language identification and speech recognition

Watanabe, S., Hori, T. & Hershey, J. R., 2018 1 24, 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 巻 2018-January. p. 265-271 7 p.

研究成果: Conference contribution

Speech recognition
Character sets
Glossaries
Network architecture
Linguistics

Model parameter learning using Kullback–Leibler divergence

Lin, C., Marks, T. K., Pajovic, M., Watanabe, S. & Tung, C. K., 2018 2 1, : : Physica A: Statistical Mechanics and its Applications. 491, p. 549-559 11 p.

研究成果: Article

Parameter Learning
Kullback-Leibler Divergence
learning
divergence
Renormalization Group

Multi-head decoder for end-to-end speech recognition

Hayashi, T., Watanabe, S., Toda, T. & Takeda, K., 2018 1 1, : : Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2018-September, p. 801-805 5 p.

研究成果: Conference article

Speech Recognition
Speech recognition
Network architecture
Linguistics
Output
9 引用 (Scopus)

Multi-level language modeling and decoding for open vocabulary end-to-end speech recognition

Hori, T., Watanabe, S. & Hershey, J. R., 2018 1 24, 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 巻 2018-January. p. 287-293 7 p.

研究成果: Conference contribution

Speech recognition
Decoding
Linguistics
8 引用 (Scopus)

Multi-modal data augmentation for end-to-end ASR

Renduchintala, A., Ding, S., Wiesner, M. & Watanabe, S., 2018 1 1, : : Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2018-September, p. 2394-2398 5 p.

研究成果: Conference article

Data Augmentation
Automatic Speech Recognition
Speech recognition
Acoustics
Error Rate
7 引用 (Scopus)

Semi-supervised end-to-end speech recognition

Karita, S., Watanabe, S., Iwata, T., Ogawa, A. & Delcroix, M., 2018 1 1, : : Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2018-September, p. 2-6 5 p.

研究成果: Conference article

Speech Recognition
Speech recognition
Text-to-speech
Encoder
Text
6 引用 (Scopus)

Speaker Adaptation for Multichannel End-to-End Speech Recognition

Ochiai, T., Watanabe, S., Katagiri, S., Hori, T. & Hershey, J., 2018 9 10, 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 巻 2018-April. p. 6707-6711 5 p. 8462161

研究成果: Conference contribution

Speech recognition
Speech enhancement
Hidden Markov models
Deep neural networks
2 引用 (Scopus)
Speech Enhancement
Speech enhancement
Memory Term
Mask
Masks
36 引用 (Scopus)
Microphones
Automatic Speech Recognition
Baseline
Speech recognition
Microphone Array
2017
55 引用 (Scopus)
Speech Recognition
Encoder
Speech recognition
Automatic Speech Recognition
Neural Networks
18 引用 (Scopus)

A Unified Architecture for Multichannel End-to-End Speech Recognition with Neural Beamforming

Ochiai, T., Watanabe, S., Hori, T., Hershey, J. R. & Xiao, X., 2017 10 17, (Accepted/In press) : : IEEE Journal on Selected Topics in Signal Processing.

研究成果: Article

Beamforming
Speech recognition
Speech enhancement
Speech analysis
Hidden Markov models
4 引用 (Scopus)

Automated structure discovery and parameter tuning of neural network language model based on evolution strategy

Tanaka, T., Moriya, T., Shinozaki, T., Watanabe, S., Hori, T. & Duh, K., 2017 2 7, 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 665-671 7 p. 7846334

研究成果: Conference contribution

Covariance matrix
Tuning
Neural networks
Recurrent neural networks
Speech recognition
4 引用 (Scopus)

Beamforming networks using spatial covariance features for far-field speech recognition

Xiao, X., Watanabe, S., Chng, E. S. & Li, H., 2017 1 17, 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016. Institute of Electrical and Electronics Engineers Inc., 7820724

研究成果: Conference contribution

Beamforming
Speech recognition
Covariance matrix
Transcription
Cost functions
2 引用 (Scopus)

BLSTM-HMM hybrid system combined with sound activity detection network for polyphonic Sound Event Detection

Hayashi, T., Watanabe, S., Toda, T., Hori, T., Le Roux, J. & Takeda, K., 2017 6 16, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 766-770 5 p. 7952259

研究成果: Conference contribution

Hidden Markov models
Hybrid systems
Acoustic waves
Recurrent neural networks
Factorization
5 引用 (Scopus)

Coupled initialization of multi-channel non-negative matrix factorization based on spatial and spectral information

Tachioka, Y., Narita, T., Miura, I., Uramoto, T., Monta, N., Uenohara, S., Furuya, K., Watanabe, S. & Le Roux, J., 2017 1 1, : : Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2017-August, p. 2461-2465 5 p.

研究成果: Conference article

Non-negative Matrix Factorization
Factorization
Initialization
Automatic Speech Recognition
Latent Variables
27 引用 (Scopus)

Deep long short-term memory adaptive beamforming networks for multichannel robust speech recognition

Meng, Z., Watanabe, S., Hershey, J. R. & Erdogan, H., 2017 6 16, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 271-275 5 p. 7952160

研究成果: Conference contribution

Beamforming
Speech recognition
Microphones
Acoustics
Memory architecture
12 引用 (Scopus)

Dialog state tracking with attention-based sequence-to-sequence learning

Hori, T., Wang, H., Hori, C., Watanabe, S., Harsham, B., Le Roux, J., Hershey, J. R., Koji, Y., Jing, Y., Zhu, Z. & Aikawa, T., 2017 2 7, 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 552-558 7 p. 7846317

研究成果: Conference contribution

Labels
Refining
Semantics
Sequence Learning
Utterance
3 引用 (Scopus)

Does speech enhancement work with end-to-end ASR objectives? Experimental analysis of multichannel end-to-end ASR

Ochiai, T., Watanabe, S. & Katagiri, S., 2017 12 5, 2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings. IEEE Computer Society, 巻 2017-September. p. 1-5 5 p.

研究成果: Conference contribution

Speech enhancement
Speech recognition
Neural networks
15 引用 (Scopus)

Duration-Controlled LSTM for Polyphonic Sound Event Detection

Hayashi, T., Watanabe, S., Toda, T., Hori, T., Le Roux, J. & Takeda, K., 2017 11 1, : : IEEE/ACM Transactions on Audio Speech and Language Processing. 25, 11, p. 2059-2070 12 p., 8010445.

研究成果: Article

Event Detection
Long-Term Memory
Memory Term
Short-Term Memory
Acoustic waves
46 引用 (Scopus)

Hybrid CTC/Attention Architecture for End-to-End Speech Recognition

Watanabe, S., Hori, T., Kim, S., Hershey, J. R. & Hayashi, T., 2017 12 1, : : IEEE Journal on Selected Topics in Signal Processing. 11, 8, p. 1240-1253 14 p., 8068205.

研究成果: Article

Speech recognition
Decoding
Linguistics
Hidden Markov models
Acoustics
19 引用 (Scopus)

Joint CTC/attention decoding for end-to-end speech recognition

Hori, T., Watanabe, S. & Hershey, J. R., 2017 1 1, ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL), 巻 1. p. 518-529 12 p.

研究成果: Conference contribution

Speech recognition
Decoding
Linguistics
linguistics
Glossaries
115 引用 (Scopus)

Joint CTC-attention based end-to-end speech recognition using multi-task learning

Kim, S., Hori, T. & Watanabe, S., 2017 6 16, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 4835-4839 5 p. 7953075

研究成果: Conference contribution

Speech recognition
Experiments