Hao-Wen Dong, Xiaoyu Liu, Jordi Pons, Gautam Bhattacharya, Santiago Pascual, Joan Serrà, Taylor Berg-Kirkpatrick, Julian J. McAuley. CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models. In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2023, New Paltz, NY, USA, October 22-25, 2023. pages 1-5, IEEE, 2023. [doi]
@inproceedings{DongLPBPSBM23,
title = {CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models},
author = {Hao-Wen Dong and Xiaoyu Liu and Jordi Pons and Gautam Bhattacharya and Santiago Pascual and Joan Serrà and Taylor Berg-Kirkpatrick and Julian J. McAuley},
year = {2023},
doi = {10.1109/WASPAA58266.2023.10248160},
url = {https://doi.org/10.1109/WASPAA58266.2023.10248160},
researchr = {https://researchr.org/publication/DongLPBPSBM23},
cites = {0},
citedby = {0},
pages = {1-5},
booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2023, New Paltz, NY, USA, October 22-25, 2023},
publisher = {IEEE},
isbn = {979-8-3503-2372-6},
}