Ziqiang Zhang, Long Zhou, Junyi Ao, Shujie Liu 0001, Lirong Dai, Jinyu Li 0001, Furu Wei. SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training. In Yoav Goldberg, Zornitsa Kozareva, Yue Zhang, editors, Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11. pages 1663-1676, Association for Computational Linguistics, 2022. [doi]
@inproceedings{ZhangZA0D0W22,
title = {SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training},
author = {Ziqiang Zhang and Long Zhou and Junyi Ao and Shujie Liu 0001 and Lirong Dai and Jinyu Li 0001 and Furu Wei},
year = {2022},
url = {https://aclanthology.org/2022.emnlp-main.108},
researchr = {https://researchr.org/publication/ZhangZA0D0W22},
cites = {0},
citedby = {0},
pages = {1663-1676},
booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11},
editor = {Yoav Goldberg and Zornitsa Kozareva and Yue Zhang},
publisher = {Association for Computational Linguistics},
}