Unsupervised training for deep speech source separation with Kullback-Leibler divergence based probabilistic loss function M Togami, Y Masuyama, T Komatsu, Y Nakagome ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 27 | 2020 |
Mentoring-Reverse Mentoring for Unsupervised Multi-Channel Speech Source Separation. Y Nakagome, M Togami, T Ogawa, T Kobayashi Interspeech, 86-90, 2020 | 14 | 2020 |
Deep speech extraction with time-varying spatial filtering guided by desired direction attractor Y Nakagome, M Togami, T Ogawa, T Kobayashi ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 6 | 2020 |
InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR Y Nakagome, T Komatsu, Y Fujita, S Ichimura, Y Kida arXiv preprint arXiv:2204.00174, 2022 | 2 | 2022 |
Efficient and stable adversarial learning using unpaired data for unsupervised multichannel speech separation Y Nakagome, M Togami, T Ogawa, T Kobayashi 22nd Annual Conference of the International Speech Communication Association …, 2021 | 2 | 2021 |
Unsupervised Training for Deep Speech Sources Separation Kullback-Leibler Divergence based Probability Loss function T Masahito, M Yoshiki, K Tatsuya, N Yu | 2 | |
Adaptive beamformer for desired source extraction with neural network based direction of arrival estimation Y Nakagome IEICE Technical Report; IEICE Tech. Rep. 118 (497), 143-147, 2019 | 1 | 2019 |
Waseda_Meisei at TRECVID 2018: Fully-automatic ad-hoc video search Y Nakagome, K Ueki, K Hirakawa, K Kikuchi, Y Hayashi, T Ogawa, ... 2018 TREC Video Retrieval Evaluation, TRECVID 2018, 2020 | | 2020 |
Adaptive Beamformer for Extracting Speech in Desired Direction Using Neural Soft-Mask Y Nakagome, M Togami, T Kobayashi IEICE Technical Report; IEICE Tech. Rep. 119 (138), 9-14, 2019 | | 2019 |