[go: up one dir, main page]

StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing

Gaoxiang Cong, Yuankai Qi, Liang Li, Amin Beheshti, Zhedong Zhang, Anton Hengel, Ming-Hsuan Yang, Chenggang Yan, Qingming Huang


Abstract
Given a script, the challenge in Movie Dubbing (Visual Voice Cloning, V2C) is to generate speech that aligns well with the video in both time and emotion, based on the tone of a reference audio track. Existing state-of-the-art V2C models break the phonemes in the script according to the divisions between video frames, which solves the temporal alignment problem but leads to incomplete phoneme pronunciation and poor identity stability. To address this problem, we propose StyleDubber, which switches dubbing learning from the frame level to phoneme level. It contains three main components: (1) A multimodal style adaptor operating at the phoneme level to learn pronunciation style from the reference audio, and generate intermediate representations informed by the facial emotion presented in the video; (2) An utterance-level style learning module, which guides both the mel-spectrogram decoding and the refining processes from the intermediate embeddings to improve the overall style expression; And (3) a phoneme-guided lip aligner to maintain lip sync. Extensive experiments on two of the primary benchmarks, V2C and Grid, demonstrate the favorable performance of the proposed method as compared to the current state-of-the-art. The code will be made available at https://github.com/GalaxyCong/StyleDubber.
Anthology ID:
2024.findings-acl.404
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6767–6779
Language:
URL:
https://aclanthology.org/2024.findings-acl.404
DOI:
10.18653/v1/2024.findings-acl.404
Bibkey:
Cite (ACL):
Gaoxiang Cong, Yuankai Qi, Liang Li, Amin Beheshti, Zhedong Zhang, Anton Hengel, Ming-Hsuan Yang, Chenggang Yan, and Qingming Huang. 2024. StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing. In Findings of the Association for Computational Linguistics: ACL 2024, pages 6767–6779, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing (Cong et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.404.pdf