Ryota Tsunoda, Ryo Aihara, Ryoichi Takashima, Tetsuya Takiguchi, Yoshie Imai. Speaker-Targeted Audio-Visual Speech Recognition Using a Hybrid CTC/Attention Model with Interference Loss. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022. pages 251-255, IEEE, 2022. [doi]
@inproceedings{TsunodaATTI22,
title = {Speaker-Targeted Audio-Visual Speech Recognition Using a Hybrid CTC/Attention Model with Interference Loss},
author = {Ryota Tsunoda and Ryo Aihara and Ryoichi Takashima and Tetsuya Takiguchi and Yoshie Imai},
year = {2022},
doi = {10.1109/ICASSP43922.2022.9747204},
url = {https://doi.org/10.1109/ICASSP43922.2022.9747204},
researchr = {https://researchr.org/publication/TsunodaATTI22},
cites = {0},
citedby = {0},
pages = {251-255},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022},
publisher = {IEEE},
isbn = {978-1-6654-0540-9},
}