渡邉 紳二

研究成果

年別の研究成果 1999 2019 2021 2022 2023

• 211 Conference contribution
• 90 Conference article
• 55 Article
• 6 Paper
• 10 その他
  • 5 Review article
  • 3 Editorial
  • 1 Book
  • 1 Chapter

年別の研究成果

年別の研究成果

検索結果

• 2023

  A dilemma of ground truth in noisy speech separation and an approach to lessen the impact of imperfect training data

  Maciejewski, M., Shi, J., Watanabe, S. & Khudanpur, S., 2023 1月, In: Computer Speech and Language. 77, 101410.

  研究成果: Article › 査読

  Open Access

  • Dilemma 100%
  • Speech 94%
  • Imperfect 80%
  • Training 75%
  • Truth 74%

• A Study on the Integration of Pre-Trained SSL, ASR, LM and SLU Models for Spoken Language Understanding

  Peng, Y., Arora, S., Higuchi, Y., Ueda, Y., Kumar, S., Ganesan, K., Dalmia, S., Chang, X. & Watanabe, S., 2023, 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 406-413 8 p. (2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings).

  研究成果: Conference contribution

  • Spoken Language Understanding 100%
  • speech recognition 79%
  • spoken language 56%
  • Speech recognition 49%
  • Benchmark 20%
  4 被引用数 (Scopus)

• A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech

  Chen, L. W., Watanabe, S. & Rudnicky, A., 2023 6月 27, AAAI-23 Technical Tracks 11. Williams, B., Chen, Y. & Neville, J. (eds.). AAAI Press, p. 12644-12652 9 p. (Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023; vol. 37).

  研究成果: Conference contribution

  • Speech synthesis 100%
  • Ablation 16%
  • Communication 6%

• CTC Alignments Improve Autoregressive Translation

  Yan, B., Dalmia, S., Higuchi, Y., Neubig, G., Metze, F., Black, A. W. & Watanabe, S., 2023, EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), p. 1615-1631 17 p. (EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference).

  研究成果: Conference contribution

  • Connectionist 100%
  • Alignment 92%
  • Automatic Speech Recognition 49%
  • Text-to-speech 25%
  • Speech recognition 25%
  5 被引用数 (Scopus)

• E-Branchformer: Branchformer with Enhanced Merging for Speech Recognition

  Kim, K., Wu, F., Peng, Y., Pan, J., Sridhar, P., Han, K. J. & Watanabe, S., 2023, 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 84-91 8 p. (2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings).

  研究成果: Conference contribution

  • Speech Recognition 100%
  • speech recognition 92%
  • convolution integrals 63%
  • Convolution 60%
  • Merging 60%
  10 被引用数 (Scopus)

• EEND-SS: Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers

  Maiti, S., Ueda, Y., Watanabe, S., Zhang, C., Yu, M., Zhang, S. X. & Xu, Y., 2023, 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 480-487 8 p. (2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings).

  研究成果: Conference contribution

  • counting 100%
  • decoders 51%
  • coders 47%
  • refining 43%
  • Refining 37%
  1 被引用数 (Scopus)

• End-to-End Integration of Speech Recognition, Dereverberation, Beamforming, and Self-Supervised Learning Representation

  Masuyama, Y., Chang, X., Cornell, S., Watanabe, S. & Ono, N., 2023, 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 260-265 6 p. (2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings).

  研究成果: Conference contribution

  • Speech Recognition 100%
  • speech recognition 92%
  • beamforming 72%
  • learning 66%
  • Supervised learning 64%
  3 被引用数 (Scopus)

• End-to-End Multi-Speaker ASR with Independent Vector Analysis

  Scheibler, R., Zhang, W., Chang, X., Watanabe, S. & Qian, Y., 2023, 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 496-501 6 p. (2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings).

  研究成果: Conference contribution

  • vector analysis 100%
  • Beamforming 43%
  • beamforming 39%
  • education 32%
  • Source separation 28%

• Improving Speech Enhancement Performance by Leveraging Contextual Broad Phonetic Class Information

  Lu, Y. J., Chang, C. Y., Yu, C., Liu, C. F., Hung, J. W., Watanabe, S. & Tsao, Y., 2023, In: IEEE/ACM Transactions on Audio Speech and Language Processing. 31, p. 2738-2750 13 p.

  研究成果: Article › 査読

  Open Access

  • Speech Enhancement 100%
  • phonetics 78%
  • Speech enhancement 65%
  • Speech analysis 62%
  • augmentation 32%

• LegoNN: Building Modular Encoder-Decoder Models

  Dalmia, S., Okhonko, D., Lewis, M., Edunov, S., Watanabe, S., Metze, F., Zettlemoyer, L. & Mohamed, A., 2023, In: IEEE/ACM Transactions on Audio Speech and Language Processing. 31, p. 3112-3126 15 p.

  研究成果: Article › 査読

  • Automatic Speech Recognition 100%
  • Machine Translation 95%
  • decoders 87%
  • Encoder 86%
  • coders 79%

• Mutual Learning of Single- and Multi-Channel End-to-End Neural Diarization

  Horiguchi, S., Takashima, Y., Watanabe, S. & Garcia, P., 2023, 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 620-625 6 p. (2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings).

  研究成果: Conference contribution

  • learning 100%
  • Distillation 18%
  • distillation 16%
  • education 12%
  • Speech processing 11%

• On Compressing Sequences for Self-Supervised Speech Models

  Meng, Y., Chen, H. J., Shi, J., Watanabe, S., Garcia, P., Lee, H. Y. & Tang, H., 2023, 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 1128-1135 8 p. (2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings).

  研究成果: Conference contribution

  • Subsampling 100%
  • compressing 91%
  • phonetics 32%
  • Speech analysis 25%
  • inference 24%
  4 被引用数 (Scopus)

• Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractors

  Horiguchi, S., Watanabe, S., Garcia, P., Takashima, Y. & Kawaguchi, Y., 2023, In: IEEE/ACM Transactions on Audio Speech and Language Processing. 31, p. 706-720 15 p.

  研究成果: Article › 査読

  Open Access

  • Global Attractor 100%
  • Attractor 85%
  • Labels 81%
  • buffers 64%
  • inference 64%
  4 被引用数 (Scopus)

• STFT-Domain Neural Speech Enhancement with Very Low Algorithmic Latency

  Wang, Z. Q., Wichern, G., Watanabe, S. & Le Roux, J., 2023, In: IEEE/ACM Transactions on Audio Speech and Language Processing. 31, p. 397-410 14 p.

  研究成果: Article › 査読

  • Speech Enhancement 100%
  • Short-time Fourier Transform 80%
  • Latency 69%
  • Speech enhancement 65%
  • Fourier transforms 52%
  7 被引用数 (Scopus)

• Superb @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning

  Feng, T. H., Dong, A., Yeh, C. F., Yang, S. W., Lin, T. Q., Shi, J., Chang, K. W., Huang, Z., Wu, H., Chang, X., Watanabe, S., Mohamed, A., Li, S. W. & Lee, H. Y., 2023, 2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 1096-1103 8 p. (2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings).

  研究成果: Conference contribution

  • learning 100%
  • Supervised learning 97%
  • efficiency 65%
  • Benchmark 42%
  • Speech Recognition 29%
  5 被引用数 (Scopus)

• TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation

  Wang, Z. Q., Cornell, S., Choi, S., Lee, Y., Kim, B. Y. & Watanabe, S., 2023, In: IEEE/ACM Transactions on Audio Speech and Language Processing. 31, p. 3221-3236 16 p.

  研究成果: Article › 査読

  • Speech 100%
  • Modeling 49%
  • Speech Enhancement 47%
  • Synchronous Meteorological Satellite 41%
  • Deep neural networks 36%
  1 被引用数 (Scopus)
• 2022

  An Empirical Study of Training Mixture Generation Strategies on Speech Separation: Dynamic Mixing and Augmentation

  Choi, S., Lee, Y., Park, J., Kim, H. Y., Kim, B. Y., Wang, Z. Q. & Watanabe, S., 2022, Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022. Institute of Electrical and Electronics Engineers Inc., p. 1070-1075 6 p. (Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022).

  研究成果: Conference contribution

  • Deep learning 100%

• AN EXPLORATION OF HUBERT WITH LARGE NUMBER OF CLUSTER UNITS AND MODEL ASSESSMENT USING Bayesian INFORMATION CRITERION

  Maekaku, T., Chang, X., Fujita, Y. & Watanabe, S., 2022, 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 7107-7111 5 p. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; vol. 2022-May).

  研究成果: Conference contribution

  • Speech recognition 100%
  • Speech analysis 62%
  • Transcription 62%
  • Supervised learning 56%
  • Syntactics 54%
  2 被引用数 (Scopus)

• An investigation of neural uncertainty estimation for target speaker extraction equipped RNN transducer

  Shi, J., Zhang, C., Weng, C., Watanabe, S., Yu, M. & Yu, D., 2022 5月, In: Computer Speech and Language. 73, 101327.

  研究成果: Article › 査読

  • Uncertainty Estimation 100%
  • Transducer 71%
  • Transducers 56%
  • Training 52%
  • Speech 52%

• Arabic speech recognition by end-to-end, modular systems and human

  Hussein, A., Watanabe, S. & Ali, A., 2022 1月, In: Computer Speech and Language. 71, 101272.

  研究成果: Article › 査読

  • Automatic Speech Recognition 100%
  • Speech Recognition 81%
  • Speech recognition 50%
  • Human 48%
  • Human Performance 46%
  16 被引用数 (Scopus)

• A review of speaker diarization: Recent advances with deep learning

  Park, T. J., Kanda, N., Dimitriadis, D., Han, K. J., Watanabe, S. & Narayanan, S., 2022 3月, In: Computer Speech and Language. 72, 101317.

  研究成果: Article › 査読

  • Speech Recognition 100%
  • Audio recordings 91%
  • Learning 89%
  • Deep learning 88%
  • Review 71%
  95 被引用数 (Scopus)

• ASR2K: Speech Recognition for Around 2000 Languages without Audio

  Li, X., Metze, F., Mortensen, D. R., Black, A. W. & Watanabe, S., 2022, In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2022-September, p. 4885-4889 5 p.

  研究成果: Conference article › 査読

  • Speech Recognition 100%
  • N-gram 66%
  • Speech recognition 57%
  • Language 44%
  • Acoustic Model 41%
  5 被引用数 (Scopus)

• Attention Weight Smoothing Using Prior Distributions for Transformer-Based End-to-End ASR

  Maekaku, T., Fujita, Y., Peng, Y. & Watanabe, S., 2022, In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2022-September, p. 1071-1075 5 p.

  研究成果: Conference article › 査読

  • Transformer 100%
  • Prior distribution 75%
  • Speech recognition 71%
  • Smoothing 69%
  • Smoothing Methods 22%
  2 被引用数 (Scopus)

• Audio-Visual Speech Recognition in MISP2021 Challenge: Dataset Release and Deep Analysis

  Chen, H., Du, J., Dai, Y., Lee, C. H., Siniscalchi, S. M., Watanabe, S., Scharenborg, O., Chen, J., Yin, B. C. & Pan, J., 2022, In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2022-September, p. 1766-1770 5 p.

  研究成果: Conference article › 査読

  • Audiovisual Speech 100%
  • Speech Recognition 96%
  • Corpus 78%
  • Audiovisual 67%
  • Vision 60%
  3 被引用数 (Scopus)

• Audio-Visual Wake Word Spotting in MISP2021 Challenge: Dataset Release and Deep Analysis

  Zhou, H., Du, J., Zou, G., Nian, Z., Lee, C. H., Siniscalchi, S. M., Watanabe, S., Scharenborg, O., Chen, J., Xiong, S. & Gao, J. Q., 2022, In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2022-September, p. 1111-1115 5 p.

  研究成果: Conference article › 査読

  • Wake 100%
  • Audiovisual 85%
  • Vision 75%
  • video 54%
  • Modality 43%
  3 被引用数 (Scopus)

• BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model

  Higuchi, Y., Yan, B., Arora, S., Ogawa, T., Kobayashi, T. & Watanabe, S., 2022, p. 5515-5532. 18 p.

  研究成果: Paper › 査読

  • Language Model 100%
  • Speech Recognition 95%
  • Speech recognition 58%
  • Formulation 39%
  • Output 17%
  2 被引用数 (Scopus)

• Better Intermediates Improve CTC Inference

  Komatsu, T., Fujita, Y., Lee, J., Lee, L., Watanabe, S. & Kida, Y., 2022, In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2022-September, p. 4965-4969 5 p.

  研究成果: Conference article › 査読

  • Conditioning 100%
  • conditioning 99%
  • Intermediate 87%
  • Inference 80%
  • Prediction 33%
  1 被引用数 (Scopus)

• Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation

  Deng, K., Watanabe, S., Shi, J. & Arora, S., 2022, In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2022-September, p. 1746-1750 5 p.

  研究成果: Conference article › 査読

  • Spoken Language Understanding 100%
  • Streaming 70%
  • Transformer 68%
  • Speech 68%
  • spoken language 56%
  5 被引用数 (Scopus)

• Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding

  Peng, Y., Dalmia, S., Lane, I. & Watanabe, S., 2022, In: Proceedings of Machine Learning Research. 162, p. 17627-17643 17 p.

  研究成果: Conference article › 査読

  • Speech Recognition 100%
  • Architecture 72%
  • Speech recognition 61%
  • Speech processing 54%
  • Speech Processing 43%
  25 被引用数 (Scopus)

• CMU’s IWSLT 2022 Dialect Speech Translation System

  Yan, B., Fernandes, P., Dalmia, S., Shi, J., Peng, Y., Berrebbi, D., Wang, X., Neubig, G. & Watanabe, S., 2022, IWSLT 2022 - 19th International Conference on Spoken Language Translation, Proceedings of the Conference. Salesky, E., Federico, M. & Costa-Jussa, M. (eds.). Association for Computational Linguistics (ACL), p. 298-307 10 p. (IWSLT 2022 - 19th International Conference on Spoken Language Translation, Proceedings of the Conference).

  研究成果: Conference contribution

  • dialect 69%
  • Machine Translation 30%
  • Connectionist 23%
  • Decoding 21%
  • Speech Recognition 15%
  10 被引用数 (Scopus)

• Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation

  Berrebbi, D., Shi, J., Yan, B., López-Francisco, O., Amith, J. & Watanabe, S., 2022, In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2022-September, p. 3533-3537 5 p.

  研究成果: Conference article › 査読

  • Speech Recognition 100%
  • Supervised Learning 87%
  • Learning Model 73%
  • Supervised learning 64%
  • Speech recognition 57%
  7 被引用数 (Scopus)

• CONDITIONAL DIFFUSION PROBABILISTIC MODEL FOR SPEECH ENHANCEMENT

  Lu, Y. J., Wang, Z. Q., Watanabe, S., Richard, A., Yu, C. & Tsao, Y., 2022, 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 7402-7406 5 p. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; vol. 2022-May).

  研究成果: Conference contribution

  • Speech enhancement 100%
  • Statistical Models 73%
  • Speech synthesis 24%
  • Experiments 7%
  40 被引用数 (Scopus)

• Deep learning based multi-source localization with source splitting and its effectiveness in multi-talker speech recognition

  Subramanian, A. S., Weng, C., Watanabe, S., Yu, M. & Yu, D., 2022 9月, In: Computer Speech and Language. 75, 101360.

  研究成果: Article › 査読

  • Automatic Speech Recognition 100%
  • Source Localization 88%
  • Speech Recognition 81%
  • Speech recognition 50%
  • Learning 48%
  29 被引用数 (Scopus)

• Deep Speech Synthesis from Articulatory Representations

  Wu, P., Watanabe, S., Goldstein, L., Black, A. W. & Anumanchipalli, G. K., 2022, In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2022-September, p. 779-783 5 p.

  研究成果: Conference article › 査読

  • Speech Synthesis 100%
  • Speech synthesis 66%
  • Synthesis 49%
  • Speech 48%
  • Speech Production 35%
  5 被引用数 (Scopus)

• Editorial Editorial of Special Issue on Self-Supervised Learning for Speech and Audio Processing

  Lee, H. Y., Watanabe, S., Livescu, K., Mohamed, A. & Sainath, T., 2022 10月 1, In: IEEE Journal on Selected Topics in Signal Processing. 16, 6, p. 1174-1178 5 p.

  研究成果: Editorial › 査読

  Open Access

• Encoder-Decoder Based Attractors for End-to-End Neural Diarization

  Horiguchi, S., Fujita, Y., Watanabe, S., Xue, Y. & Garcia, P., 2022, In: IEEE/ACM Transactions on Audio Speech and Language Processing. 30, p. 1493-1507 15 p.

  研究成果: Article › 査読

  Open Access

  • decoders 100%
  • Encoder 98%
  • coders 91%
  • Attractor 66%
  • Detectors 57%
  18 被引用数 (Scopus)

• End-to-End Dereverberation, Beamforming, and Speech Recognition in a Cocktail Party

  Zhang, W., Chang, X., Boeddeker, C., Nakatani, T., Watanabe, S. & Qian, Y., 2022, In: IEEE/ACM Transactions on Audio Speech and Language Processing. 30, p. 3173-3188 16 p.

  研究成果: Article › 査読

  • Automatic Speech Recognition 100%
  • Beamforming 86%
  • Speech Recognition 81%
  • speech recognition 81%
  • beamforming 63%
  7 被引用数 (Scopus)

• End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation

  Chang, X., Maekaku, T., Fujita, Y. & Watanabe, S., 2022, In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2022-September, p. 3819-3823 5 p.

  研究成果: Conference article › 査読

  • Speech Enhancement 100%
  • Speech Recognition 86%
  • Supervised Learning 75%
  • Speech enhancement 65%
  • Supervised learning 56%
  6 被引用数 (Scopus)

• ESPnet-ONNX: Bridging a Gap Between Research and Production

  Someki, M., Higuchi, Y., Hayashi, T. & Watanabe, S., 2022, Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022. Institute of Electrical and Electronics Engineers Inc., p. 420-427 8 p. (Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022).

  研究成果: Conference contribution

  • Speech processing 100%
  • Deep learning 71%
  • Neural networks 48%
  1 被引用数 (Scopus)

• ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding

  Lu, Y. J., Chang, X., Li, C., Zhang, W., Cornell, S., Ni, Z., Masuyama, Y., Yan, B., Scheibler, R., Wang, Z. Q., Tsao, Y., Qian, Y. & Watanabe, S., 2022, In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2022-September, p. 5458-5462 5 p.

  研究成果: Conference article › 査読

  • Speech Enhancement 100%
  • Speech Recognition 86%
  • Speech 69%
  • Speech enhancement 65%
  • Enhancement 54%
  8 被引用数 (Scopus)

• ESPNET-SLU: ADVANCING SPOKEN LANGUAGE UNDERSTANDING THROUGH ESPNET

  Arora, S., Dalmia, S., Denisov, P., Chang, X., Ueda, Y., Peng, Y., Zhang, Y., Kumar, S., Ganesan, K., Yan, B., Vu, N. T., Black, A. W. & Watanabe, S., 2022, 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 7167-7171 5 p. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; vol. 2022-May).

  研究成果: Conference contribution

  • Speech processing 100%
  27 被引用数 (Scopus)

• EXTENDED GRAPH TEMPORAL CLASSIFICATION FOR MULTI-SPEAKER END-TO-END ASR

  Chang, X., Moritz, N., Hori, T., Watanabe, S. & Le Roux, J., 2022, 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 7322-7326 5 p. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; vol. 2022-May).

  研究成果: Conference contribution

  • Speech recognition 100%
  • Labels 38%
  • Semi-supervised learning 18%
  • Transcription 17%
  • Computer simulation 16%
  1 被引用数 (Scopus)

• FINDINGS OF THE IWSLT 2022 EVALUATION CAMPAIGN

  Anastasopoulos, A., Barrault, L., Bentivogli, L., Boito, M. Z., Bojar, O., Cattoni, R., Currey, A., Dinu, G., Duh, K., Elbayad, M., Emmanuel, C., Estève, Y., Federico, M., Federmann, C., Gahbiche, S., Gong, H., Grundkiewicz, R., Haddow, B., Hsu, B., Javorský, D., & 23 othersKloudová, V., Lakew, S. M., Ma, X., Mathur, P., McNamee, P., Murray, K., Nădejde, M., Nakamura, S., Negri, M., Niehues, J., Niu, X., Ortega, J., Pino, J., Salesky, E., Shi, J., Sperber, M., Stüker, S., Sudoh, K., Turchi, M., Virkar, Y., Waibel, A., Wang, C. & Watanabe, S., 2022, IWSLT 2022 - 19th International Conference on Spoken Language Translation, Proceedings of the Conference. Salesky, E., Federico, M. & Costa-Jussa, M. (eds.). Association for Computational Linguistics (ACL), p. 98-157 60 p. (IWSLT 2022 - 19th International Conference on Spoken Language Translation, Proceedings of the Conference).

  研究成果: Conference contribution

  • campaign 100%
  • Evaluation 72%
  • evaluation 61%
  • Speech-to-speech Translation 33%
  • Formality 21%
  67 被引用数 (Scopus)

• HEAR: Holistic Evaluation of Audio Representations

  Turian, J., Shier, J., Khan, H. R., Raj, B., Schuller, B. W., Steinmetz, C. J., Malloy, C., Tzanetakis, G., Velarde, G., McNally, K., Henry, M., Pinto, N., Noufi, C., Clough, C., Herremans, D., Fonseca, E., Engel, J., Salamon, J., Esling, P., Manocha, P., & 3 othersWatanabe, S., Jin, Z. & Bisk, Y., 2022, In: Proceedings of Machine Learning Research. 176, p. 125-145 21 p.

  研究成果: Conference article › 査読

  • Evaluation 100%
  • Benchmark 89%
  • Comprehensive Evaluation 81%
  • Open Source 62%
  • Speech 60%
  21 被引用数 (Scopus)

• Improving Frame-Online Neural Speech Enhancement With Overlapped-Frame Prediction

  Wang, Z. Q. & Watanabe, S., 2022, In: IEEE Signal Processing Letters. 29, p. 1422-1426 5 p.

  研究成果: Article › 査読

  • Speech Enhancement 100%
  • Speech enhancement 65%
  • Prediction 42%
  • Fourier transforms 34%
  • Short-time Fourier Transform 23%
  1 被引用数 (Scopus)

• IMPROVING NON-AUTOREGRESSIVE END-TO-END SPEECH RECOGNITION WITH PRE-TRAINED ACOUSTIC AND LANGUAGE MODELS

  Deng, K., Yang, Z., Watanabe, S., Higuchi, Y., Cheng, G. & Zhang, P., 2022, 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 8522-8526 5 p. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; vol. 2022-May).

  研究成果: Conference contribution

  • Speech recognition 100%
  • Acoustics 86%
  • Decoding 45%
  9 被引用数 (Scopus)

• Improving Speech Enhancement through Fine-Grained Speech Characteristics

  Yang, M., Konan, J., Bick, D., Kumar, A., Watanabe, S. & Raj, B., 2022, In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2022-September, p. 2953-2957 5 p.

  研究成果: Conference article › 査読

  • Speech Enhancement 100%
  • Speech 69%
  • Speech enhancement 65%
  • Enhancement 54%
  • Speech Signal 43%
  3 被引用数 (Scopus)

• INTEGRATING MULTIPLE ASR SYSTEMS INTO NLP BACKEND WITH ATTENTION FUSION

  Kano, T., Ogawa, A., Delcroix, M. & Watanabe, S., 2022, 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 6237-6241 5 p. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; vol. 2022-May).

  研究成果: Conference contribution

  • Natural language processing systems 100%
  • Speech recognition 76%
  • Fusion reactions 65%
  • Transcription 13%
  • Experiments 4%
  2 被引用数 (Scopus)

• INVESTIGATING SELF-SUPERVISED LEARNING FOR SPEECH ENHANCEMENT AND SEPARATION

  Huang, Z., Watanabe, S., Yang, S. W., García, P. & Khudanpur, S., 2022, 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 6837-6841 5 p. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; vol. 2022-May).

  研究成果: Conference contribution

  • Speech enhancement 100%
  • Supervised learning 85%
  • Speech processing 14%
  • Fourier transforms 11%
  25 被引用数 (Scopus)

• JOINT MODELING OF CODE-SWITCHED AND MONOLINGUAL ASR VIA CONDITIONAL FACTORIZATION

  Yan, B., Zhang, C., Yu, M., Zhang, S. X., Dalmia, S., Berrebbi, D., Weng, C., Watanabe, S. & Yu, D., 2022, 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 6412-6416 5 p. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; vol. 2022-May).

  研究成果: Conference contribution

  • Factorization 100%
  • Speech recognition 94%
  • Computer simulation 54%
  • Labels 42%
  • Synchronization 40%
  5 被引用数 (Scopus)