StyleDubber: towards multi-scale style learning for movie dubbing

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

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

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.

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics ACL 2024
Place of PublicationKerrville
PublisherAssociation for Computational Linguistics
Pages6767-6779
Number of pages13
ISBN (Electronic)9798891760998
DOIs
Publication statusPublished - 2024
EventAnnual Meeting of the Association for Computational Linguistics (62nd : 2024) - Virtual; Bangkok, Thailand
Duration: 11 Aug 202416 Aug 2024

Conference

ConferenceAnnual Meeting of the Association for Computational Linguistics (62nd : 2024)
Abbreviated titleACL 2024
Country/TerritoryThailand
CityVirtual; Bangkok
Period11/08/2416/08/24

Cite this