Sravya Popuri, Peng-Jen Chen, Changhan Wang, Juan Pino, Yossi Adi, Jiatao Gu, Wei-Ning Hsu, Ann Lee. Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation. In Hanseok Ko, John H. L. Hansen, editors, Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022. pages 5195-5199, ISCA, 2022. [doi]
@inproceedings{PopuriCWPAGHL22,
title = {Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation},
author = {Sravya Popuri and Peng-Jen Chen and Changhan Wang and Juan Pino and Yossi Adi and Jiatao Gu and Wei-Ning Hsu and Ann Lee},
year = {2022},
doi = {10.21437/Interspeech.2022-11032},
url = {https://doi.org/10.21437/Interspeech.2022-11032},
researchr = {https://researchr.org/publication/PopuriCWPAGHL22},
cites = {0},
citedby = {0},
pages = {5195-5199},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022},
editor = {Hanseok Ko and John H. L. Hansen},
publisher = {ISCA},
}