Audio-Visual Speech Representation Expert for Enhanced Talking Face Video Generation and Evaluation
Abstract
In the task of talking face generation, the objective is to generate a face video with lips synchronized to the corresponding audio while preserving visual details and identity information. Current methods face the challenge of learning accurate lip synchronization while avoiding detrimental effects on visual quality, as well as robustly evaluating such synchronization. To tackle these problems, we propose utilizing an audio-visual speech representation expert (AV-HuBERT) for calculating lip synchronization loss during training. Moreover, leveraging AV-HuBERT’s features, we introduce three novel lip synchronization evaluation metrics, aiming to provide a comprehensive assessment of lip synchronization performance. Experimental results, along with a detailed ablation study, demonstrate the effectiveness of our approach and the utility of the proposed evaluation metrics.
Cite
Text
Yaman et al. "Audio-Visual Speech Representation Expert for Enhanced Talking Face Video Generation and Evaluation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024. doi:10.1109/CVPRW63382.2024.00607Markdown
[Yaman et al. "Audio-Visual Speech Representation Expert for Enhanced Talking Face Video Generation and Evaluation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024.](https://mlanthology.org/cvprw/2024/yaman2024cvprw-audiovisual/) doi:10.1109/CVPRW63382.2024.00607BibTeX
@inproceedings{yaman2024cvprw-audiovisual,
title = {{Audio-Visual Speech Representation Expert for Enhanced Talking Face Video Generation and Evaluation}},
author = {Yaman, Dogucan and Eyiokur, Fevziye Irem and Bärmann, Leonard and Akti, Seymanur and Ekenel, Hazim Kemal and Waibel, Alexander},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2024},
pages = {6003-6013},
doi = {10.1109/CVPRW63382.2024.00607},
url = {https://mlanthology.org/cvprw/2024/yaman2024cvprw-audiovisual/}
}