Towards Expressive Video Dubbing with Multiscale Multimodal Context Interaction

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhao, Yuan, Liu, Rui, Cong, Gaoxiang
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929653522890752
author Zhao, Yuan
Liu, Rui
Cong, Gaoxiang
author_facet Zhao, Yuan
Liu, Rui
Cong, Gaoxiang
contents Automatic Video Dubbing (AVD) generates speech aligned with lip motion and facial emotion from scripts. Recent research focuses on modeling multimodal context to enhance prosody expressiveness but overlooks two key issues: 1) Multiscale prosody expression attributes in the context influence the current sentence's prosody. 2) Prosody cues in context interact with the current sentence, impacting the final prosody expressiveness. To tackle these challenges, we propose M2CI-Dubber, a Multiscale Multimodal Context Interaction scheme for AVD. This scheme includes two shared M2CI encoders to model the multiscale multimodal context and facilitate its deep interaction with the current sentence. By extracting global and local features for each modality in the context, utilizing attention-based mechanisms for aggregation and interaction, and employing an interaction-based graph attention network for fusion, the proposed approach enhances the prosody expressiveness of synthesized speech for the current sentence. Experiments on the Chem dataset show our model outperforms baselines in dubbing expressiveness. The code and demos are available at \textcolor[rgb]{0.93,0.0,0.47}{https://github.com/AI-S2-Lab/M2CI-Dubber}.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18748
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Expressive Video Dubbing with Multiscale Multimodal Context Interaction
Zhao, Yuan
Liu, Rui
Cong, Gaoxiang
Multimedia
Computation and Language
Sound
Audio and Speech Processing
Automatic Video Dubbing (AVD) generates speech aligned with lip motion and facial emotion from scripts. Recent research focuses on modeling multimodal context to enhance prosody expressiveness but overlooks two key issues: 1) Multiscale prosody expression attributes in the context influence the current sentence's prosody. 2) Prosody cues in context interact with the current sentence, impacting the final prosody expressiveness. To tackle these challenges, we propose M2CI-Dubber, a Multiscale Multimodal Context Interaction scheme for AVD. This scheme includes two shared M2CI encoders to model the multiscale multimodal context and facilitate its deep interaction with the current sentence. By extracting global and local features for each modality in the context, utilizing attention-based mechanisms for aggregation and interaction, and employing an interaction-based graph attention network for fusion, the proposed approach enhances the prosody expressiveness of synthesized speech for the current sentence. Experiments on the Chem dataset show our model outperforms baselines in dubbing expressiveness. The code and demos are available at \textcolor[rgb]{0.93,0.0,0.47}{https://github.com/AI-S2-Lab/M2CI-Dubber}.
title Towards Expressive Video Dubbing with Multiscale Multimodal Context Interaction
topic Multimedia
Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2412.18748