Pith. sign in

REVIEW 1 cited by

StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.12636 v3 pith:TT5FETZW submitted 2024-02-20 cs.CL

classification cs.CL
keywords styledubbinglearninglevelphonemestyledubbervideoaudio
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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 stateof-the-art. The code will be made available at https://github.com/GalaxyCong/StyleDubber.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MM-MovieDubber: Towards Multi-Modal Learning for Multi-Modal Movie Dubbing

    cs.MM 2025-05 conditional novelty 5.0 of 10

    A movie dubbing system that uses a vision-language model to extract scene type and speaker attributes from silent video, then feeds those attributes as extra conditions into a diffusion-based speech generator, support...

Pith tools