VCVTS: Multi-Speaker Video-to-Speech Synthesis Via Cross-Modal Knowledge Transfer from Voice Conversion-Reference-Cited by-同舟云学术

VCVTS: Multi-Speaker Video-to-Speech Synthesis Via Cross-Modal Knowledge Transfer from Voice Conversion

Published:2022-05-23 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Wang Disong¹,Yang Shan²,Su Dan²,Liu Xunying¹,Yu Dong²,Meng Helen¹

Affiliation:

1. The Chinese University of Hong Kong,Hong Kong SAR, China

2. Tencent AI lab,China

Publisher

IEEE

Link

Reference39 articles.

1. Visualizing data using t-sne;van der maaten;Journal of Machine Learning Research,2008

4. mixup: Beyond empirical risk minimization;zhang;arXiv preprint arXiv 1710 09412,2017

Cited by 8 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

2. RobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting Self-Supervised Representations;2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC);2023-10-31

3. Face-Driven Zero-Shot Voice Conversion with Memory-based Face-Voice Alignment;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26

4. Multi-Speaker Speech Synthesis from Electromyographic Signals by Soft Speech Unit Prediction;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04

5. Zero-Shot Personalized Lip-To-Speech Synthesis with Face Image Based Voice Control;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04