フォロー
Tatsuya Komatsu
Tatsuya Komatsu
LINE Corporation
確認したメール アドレス: linecorp.com
タイトル
引用先
引用先
Weakly-supervised sound event detection with self-attention
K Miyazaki, T Komatsu, T Hayashi, S Watanabe, T Toda, K Takeda
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
832020
Acoustic Event Detection Method Using Semi-Supervised Non-Negative Matrix Factorization with Mixtures of Local Dictionaries.
T Komatsu, T Toizumi, R Kondo, Y Senda
DCASE, 45-49, 2016
832016
Convolution-augmented transformer for semi-supervised sound event detection
K Miyazaki, T Komatsu, T Hayashi, S Watanabe, T Toda, K Takeda
Proc. workshop detection classification Acoust. Scenes events (DCASE), 100-104, 2020
782020
Relaxing the conditional independence assumption of CTC-based ASR by conditioning on intermediate predictions
J Nozaki, T Komatsu
arXiv preprint arXiv:2104.02724, 2021
632021
Conformer-based sound event detection with semi-supervised learning and data augmentation
K Miyazaki, T Komatsu, T Hayashi, S Watanabe, T Toda, K Takeda
dim 1 (4), 2020
522020
A comparative study on non-autoregressive modelings for speech-to-text generation
Y Higuchi, N Chen, Y Fujita, H Inaguma, T Komatsu, J Lee, J Nozaki, ...
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 47-54, 2021
462021
Acoustic event detection based on non-negative matrix factorization with mixtures of local dictionaries and activation aggregation
T Komatsu, Y Senda, R Kondo
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
452016
Anomalous sound event detection based on wavenet
T Hayashi, T Komatsu, R Kondo, T Toda, K Takeda
2018 26th European Signal Processing Conference (EUSIPCO), 2494-2498, 2018
422018
Disentangled speaker and language representations using mutual information minimization and domain adaptation for cross-lingual tts
D Xin, T Komatsu, S Takamichi, H Saruwatari
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
282021
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
272020
Detection of anomaly acoustic scenes based on a temporal dissimilarity model
T Komatsu, R Kondo
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
132017
Initial stage of Pd adsorption on Si (111) 7× 7 surface studied by AES and EELS
S Nishigaki, T Komatsu, M Arimoto, M Sugihara
Surface science 167 (1), 27-38, 1986
131986
Scene-dependent acoustic event detection with scene conditioning and fake-scene-conditioned loss
T Komatsu, K Imoto, M Togami
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
122020
Neural diarization with non-autoregressive intermediate attractors
Y Fujita, T Komatsu, R Scheibler, Y Kida, T Ogawa
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
112023
Multichannel loss function for supervised speech source separation by mask-based beamforming
Y Masuyama, M Togami, T Komatsu
arXiv preprint arXiv:1907.04984, 2019
112019
Robust acoustic scene classification to multiple devices using maximum classifier discrepancy and knowledge distillation
S Takeyama, T Komatsu, K Miyazaki, M Togami, S Ono
2020 28th European Signal Processing Conference (EUSIPCO), 36-40, 2021
102021
Sound event localization and detection using convolutional recurrent neural networks and gated linear units
T Komatsu, M Togami, T Takahashi
2020 28th European Signal Processing Conference (EUSIPCO), 41-45, 2021
102021
Consistency-aware multi-channel speech enhancement using deep neural networks
Y Masuyama, M Togami, T Komatsu
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
102020
Scene-dependent anomalous acoustic-event detection based on conditional Wavenet and I-vector
T Komatsu, T Hayashiy, R Kondo, T Todaz, K Takeday
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
92019
MLP-based architecture with variable length input for automatic speech recognition
J Sakuma, T Komatsu, R Scheibler
82021
現在システムで処理を実行できません。しばらくしてからもう一度お試しください。
論文 1–20