TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Ji-Hoon, Ahn, Junseok, Kwak, Doyeop, Chung, Joon Son, Watanabe, Shinji
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909974658023424
author Kim, Ji-Hoon
Ahn, Junseok
Kwak, Doyeop
Chung, Joon Son
Watanabe, Shinji
author_facet Kim, Ji-Hoon
Ahn, Junseok
Kwak, Doyeop
Chung, Joon Son
Watanabe, Shinji
contents The objective of this paper is to jointly synthesize interactive videos and conversational speech from text and reference images. With the ultimate goal of building human-like conversational systems, recent studies have explored talking or listening head generation as well as conversational speech generation. However, these works are typically studied in isolation, overlooking the multimodal nature of human conversation, which involves tightly coupled audio-visual interactions. In this paper, we introduce TAVID, a unified framework that generates both interactive faces and conversational speech in a synchronized manner. TAVID integrates face and speech generation pipelines through two cross-modal mappers (i.e., a motion mapper and a speaker mapper), which enable bidirectional exchange of complementary information between the audio and visual modalities. We evaluate our system across four dimensions: talking face realism, listening head responsiveness, dyadic interaction fluency, and speech quality. Extensive experiments demonstrate the effectiveness of our approach across all these aspects.
format Preprint
id arxiv_https___arxiv_org_abs_2512_20296
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation
Kim, Ji-Hoon
Ahn, Junseok
Kwak, Doyeop
Chung, Joon Son
Watanabe, Shinji
Computer Vision and Pattern Recognition
Artificial Intelligence
Audio and Speech Processing
Image and Video Processing
The objective of this paper is to jointly synthesize interactive videos and conversational speech from text and reference images. With the ultimate goal of building human-like conversational systems, recent studies have explored talking or listening head generation as well as conversational speech generation. However, these works are typically studied in isolation, overlooking the multimodal nature of human conversation, which involves tightly coupled audio-visual interactions. In this paper, we introduce TAVID, a unified framework that generates both interactive faces and conversational speech in a synchronized manner. TAVID integrates face and speech generation pipelines through two cross-modal mappers (i.e., a motion mapper and a speaker mapper), which enable bidirectional exchange of complementary information between the audio and visual modalities. We evaluate our system across four dimensions: talking face realism, listening head responsiveness, dyadic interaction fluency, and speech quality. Extensive experiments demonstrate the effectiveness of our approach across all these aspects.
title TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Audio and Speech Processing
Image and Video Processing
url https://arxiv.org/abs/2512.20296