OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Luo, Cheng, Wang, Jianghui, Li, Bing, Song, Siyang, Ghanem, Bernard
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912673216593920
author Luo, Cheng
Wang, Jianghui
Li, Bing
Song, Siyang
Ghanem, Bernard
author_facet Luo, Cheng
Wang, Jianghui
Li, Bing
Song, Siyang
Ghanem, Bernard
contents In this paper, we introduce Online Multimodal Conversational Response Generation (OMCRG), a novel task designed to produce synchronized verbal and non-verbal listener feedback online, based on the speaker's multimodal inputs. OMCRG captures natural dyadic interactions and introduces new challenges in aligning generated audio with listeners' facial responses. To tackle these challenges, we incorporate text as an intermediate modality to connect audio and facial responses. We propose OmniResponse, a Multimodal Large Language Model (MLLM) that autoregressively generates accurate multimodal listener responses. OmniResponse leverages a pretrained LLM enhanced with two core components: Chrono-Text Markup, which precisely timestamps generated text tokens, and TempoVoice, a controllable online text-to-speech (TTS) module that outputs speech synchronized with facial responses. To advance OMCRG research, we offer ResponseNet, a dataset of 696 detailed dyadic interactions featuring synchronized split-screen videos, multichannel audio, transcripts, and annotated facial behaviors. Comprehensive evaluations on ResponseNet demonstrate that OmniResponse outperforms baseline models in terms of semantic speech content, audio-visual synchronization, and generation quality. Our dataset, code, and models are publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21724
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions
Luo, Cheng
Wang, Jianghui
Li, Bing
Song, Siyang
Ghanem, Bernard
Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
In this paper, we introduce Online Multimodal Conversational Response Generation (OMCRG), a novel task designed to produce synchronized verbal and non-verbal listener feedback online, based on the speaker's multimodal inputs. OMCRG captures natural dyadic interactions and introduces new challenges in aligning generated audio with listeners' facial responses. To tackle these challenges, we incorporate text as an intermediate modality to connect audio and facial responses. We propose OmniResponse, a Multimodal Large Language Model (MLLM) that autoregressively generates accurate multimodal listener responses. OmniResponse leverages a pretrained LLM enhanced with two core components: Chrono-Text Markup, which precisely timestamps generated text tokens, and TempoVoice, a controllable online text-to-speech (TTS) module that outputs speech synchronized with facial responses. To advance OMCRG research, we offer ResponseNet, a dataset of 696 detailed dyadic interactions featuring synchronized split-screen videos, multichannel audio, transcripts, and annotated facial behaviors. Comprehensive evaluations on ResponseNet demonstrate that OmniResponse outperforms baseline models in terms of semantic speech content, audio-visual synchronization, and generation quality. Our dataset, code, and models are publicly available.
title OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2505.21724