| Making Punctuation Restoration Robust and Fast with Multi-Task Learning and Knowledge Distillation M Hentschel, E Tsunoo, T Okuda ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 14 | 2021 |
| Joint Speech Recognition and Audio Captioning C Narisetty, E Tsunoo, X Chang, Y Kashiwagi, M Hentschel, S Watanabe ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 8 | 2022 |
| Feature based domain adaptation for neural network language models with factorised hidden layers M Hentschel, M Delcroix, A Ogawa, T Iwata, T Nakatani IEICE transactions on Information and Systems 102 (3), 598-608, 2019 | 8 | 2019 |
| Sound event localization and detection with pre-trained audio spectrogram transformer and multichannel separation network R Scheibler, T Komatsu, Y Fujita, M Hentschel omni (1ch) 13 (4ch), 5x13x497, 2022 | 7 | 2022 |
| A unified framework for feature-based domain adaptation of neural network language models M Hentschel, M Delcroix, A Ogawa, T Iwata, T Nakatani ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 5 | 2019 |
| Feature-Based Learning Hidden Unit Contributions for Domain Adaptation of RNN-LMs M Hentschel, M Delcroix, A Ogawa, T Nakatani 2018 Asia-Pacific Signal and Information Processing Association Annual …, 2018 | 4 | 2018 |
| Run-and-back stitch search: novel block synchronous decoding for streaming encoder-decoder ASR E Tsunoo, C Narisetty, M Hentschel, Y Kashiwagi, S Watanabe ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 3 | 2022 |
| On Sorting and Padding Multiple Targets for Sound Event Localization and Detection with Permutation Invariant and Location-based Training R Scheibler, T Komatsu, Y Fujita, M Hentschel 2022 Asia-Pacific Signal and Information Processing Association Annual …, 2022 | 2 | 2022 |
| 3D CNN AND CONFORMER WITH AUDIO SPECTROGRAM TRANSFORMER FOR SOUND EVENT DETECTION AND LOCALIZATION R Scheibler, T Komatsu, Y Fujita, M Hentschel DCASE2022 Challenge, 2022 | 2 | 2022 |
| Apparatus, method, and program for utilizing language model M Delcroix, A Ogawa, T Nakatani, M Hentschel US Patent App. 16/976,692, 2021 | 2 | 2021 |
| Factorised hidden layer based domain adaptation for recurrent neural network language models M Hentschel, M Delcroix, A Ogawa, T Iwata, T Nakatani 2018 Asia-Pacific Signal and Information Processing Association Annual …, 2018 | 2 | 2018 |
| Exploiting imbalanced textual and acoustic data for training prosodically-enhanced RNNLMs M Hentschel, A Ogawa, M Delcroix, T Nakatani, Y Matsumoto 2017 Asia-Pacific Signal and Information Processing Association Annual …, 2017 | 1 | 2017 |
| Unfolded Deep Recurrent Convolutional Neural Network with Jump Ahead Connections for Acoustic Modeling. DT Tran, M Delcroix, S Karita, M Hentschel, A Ogawa, T Nakatani INTERSPEECH, 1596-1600, 2017 | 1 | 2017 |
| Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers M Hentschel, Y Nishikawa, T Komatsu, Y Fujita arXiv preprint arXiv:2401.11700, 2024 | | 2024 |
| Context Enhancement of Recurrent Neural Network Language Models for Automatic Speech Recognition MA Hentschel (No Title), 2019 | | 2019 |
Tomohiro NakataniNTT Communication Science Laboratories確認したメール アドレス: ieee.org
