Sara Papi, Peidong Wang, Junkun Chen, Jian Xue, Jinyu Li 0001, Yashesh Gaur. Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignments. In IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023, Taipei, Taiwan, December 16-20, 2023. pages 1-8, IEEE, 2023. [doi]
@inproceedings{PapiWCXLG23,
title = {Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignments},
author = {Sara Papi and Peidong Wang and Junkun Chen and Jian Xue and Jinyu Li 0001 and Yashesh Gaur},
year = {2023},
doi = {10.1109/ASRU57964.2023.10389715},
url = {https://doi.org/10.1109/ASRU57964.2023.10389715},
researchr = {https://researchr.org/publication/PapiWCXLG23},
cites = {0},
citedby = {0},
pages = {1-8},
booktitle = {IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023, Taipei, Taiwan, December 16-20, 2023},
publisher = {IEEE},
isbn = {979-8-3503-0689-7},
}