Takaki Makino, Hank Liao, Yannis M. Assael, Brendan Shillingford, Basilio Garcia, Otavio Braga, Olivier Siohan. Recurrent Neural Network Transducer for Audio-Visual Speech Recognition. In IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019, Singapore, December 14-18, 2019. pages 905-912, IEEE, 2019. [doi]
@inproceedings{MakinoLASGBS19,
title = {Recurrent Neural Network Transducer for Audio-Visual Speech Recognition},
author = {Takaki Makino and Hank Liao and Yannis M. Assael and Brendan Shillingford and Basilio Garcia and Otavio Braga and Olivier Siohan},
year = {2019},
doi = {10.1109/ASRU46091.2019.9004036},
url = {https://doi.org/10.1109/ASRU46091.2019.9004036},
researchr = {https://researchr.org/publication/MakinoLASGBS19},
cites = {0},
citedby = {0},
pages = {905-912},
booktitle = {IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019, Singapore, December 14-18, 2019},
publisher = {IEEE},
isbn = {978-1-7281-0306-8},
}