Disong Wang, Shan Yang, Dan Su 0002, Xunying Liu, Dong Yu 0001, Helen Meng. VCVTS: Multi-Speaker Video-to-Speech Synthesis Via Cross-Modal Knowledge Transfer from Voice Conversion. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022. pages 7252-7256, IEEE, 2022. [doi]
@inproceedings{WangYSLYM22,
title = {VCVTS: Multi-Speaker Video-to-Speech Synthesis Via Cross-Modal Knowledge Transfer from Voice Conversion},
author = {Disong Wang and Shan Yang and Dan Su 0002 and Xunying Liu and Dong Yu 0001 and Helen Meng},
year = {2022},
doi = {10.1109/ICASSP43922.2022.9747427},
url = {https://doi.org/10.1109/ICASSP43922.2022.9747427},
researchr = {https://researchr.org/publication/WangYSLYM22},
cites = {0},
citedby = {0},
pages = {7252-7256},
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},
}