关注
Tetsuji Ogawa
标题
引用次数
引用次数
年份
Mask CTC: Non-autoregressive end-to-end ASR with CTC and mask predict
Y Higuchi, S Watanabe, N Chen, T Ogawa, T Kobayashi
arXiv preprint arXiv:2005.08700, 2020
1372020
Improved Mask-CTC for non-autoregressive end-to-end ASR
Y Higuchi, H Inaguma, S Watanabe, T Ogawa, T Kobayashi
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
682021
CHARM-deep: Continuous human activity recognition model based on deep neural network using IMU sensors of smartwatch
S Ashry, T Ogawa, W Gomaa
IEEE Sensors Journal 20 (15), 8757-8770, 2020
592020
Block-wise scrambled image recognition using adaptation network
K Madono, M Tanaka, M Onishi, T Ogawa
arXiv preprint arXiv:2001.07761, 2020
542020
CENSREC-1-AV: An audio-visual corpus for noisy bimodal speech recognition
S. Tamura, C. Miyajima, N. Kitaoka, T. Yamada, S. Tsuge, T. Takiguchi, K ...
Proc. The 9th International Conference on Auditory-Visual Speech Processing …, 2010
52*2010
Tandem connectionist anomaly detection: Use of faulty vibration signals in feature representation learning
T Hasegawa, J Ogata, M Murakawa, T Ogawa
2018 IEEE International Conference on Prognostics and Health Management …, 2018
46*2018
Multi-Channel Speech Enhancement Using Time-Domain Convolutional Denoising Autoencoder.
N Tawara, T Kobayashi, T Ogawa
Proc. The 20th Annual Conference of the International Speech Communication …, 2019
422019
Real-time large-scale map matching using mobile phone data
E Algizawy, T Ogawa, A El-Mahdy
ACM Transactions on Knowledge Discovery from Data (TKDD) 11 (4), 1-38, 2017
422017
Waseda Meisei at TRECVID 2017: Ad-hoc Video Search.
K Ueki, K Hirakawa, K Kikuchi, T Ogawa, T Kobayashi
Notebook paper of the TRECVID 2017 Workshop, 2017
412017
CENSREC-1-C: An evaluation framework for voice activity detection under noisy environments
N. Kitaoka, T. Yamada, S. Tsuge, C. Miyajima, K. Yamamoto, T. Nishiura, M ...
Acoust. Sci., & Tech. 30 (5), 363-371, 2009
412009
CENSREC-4: development of evaluation framework for distant-talking speech recognition under reverberant environments
M. Nakayama, T. Nishiura, Y. Denda, N. Kitaoka, K. Yamamoto, T. Yamada, S ...
Ninth Annual Conference of the International Speech Communication …, 2008
41*2008
Speaker invariant feature extraction for zero-resource languages with adversarial training
T Tsuchiya, N Tawara, T Kobayashi, T Ogawa
Proc. 2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
372018
Uncertainty estimation of DNN classifiers
SH Mallidi, T Ogawa, H Hermansky
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
342015
Frame-level phoneme-invariant speaker embedding for text-independent speaker recognition on extremely short utterances
N Tawara, A Ogawa, T Iwata, M Delcroix, T Ogawa
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
322020
Visual explanation of neural network based rotation machinery anomaly detection system
M Saeki, J Ogata, M Murakawa, T Ogawa
2019 IEEE International Conference on Prognostics and Health Management …, 2019
292019
Autoencoder based multi-stream combination for noise robust speech recognition
S. H. Mallidi, T. Ogawa, K. Vesely, P. S. Nidadavolu, H. Hermansky
INTERSPEECH2015, 3551-3555, 2015
282015
Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
Y Higuchi, K Karube, T Ogawa, T Kobayashi
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
272022
BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model
Y Higuchi, B Yan, S Arora, T Ogawa, T Kobayashi, S Watanabe
Proc. The 2022 Conference on Empirical Methods in Natural Language …, 2022
242022
SIA-GAN: Scrambling inversion attack using generative adversarial network
K Madono, M Tanaka, M Onishi, T Ogawa
IEEE Access 9, 129385-129393, 2021
202021
Adaptive training of vibration-based anomaly detector for wind turbine condition monitoring
T Hasegawa, J Ogata, M Murakawa, T Kobayashi, T Ogawa
Annual Conference on PHM Society, 177-184, 2017
162017
系统目前无法执行此操作,请稍后再试。
文章 1–20