MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and Generation

TL;DR

MAViD introduces a multimodal framework that effectively integrates audio-visual understanding and generation for dialogue systems, enabling coherent, long-duration interactions with improved fusion and control.

Contribution

The paper presents a Conductor-Creator architecture with novel fusion and dual generative models, advancing multimodal dialogue understanding and generation capabilities.

Findings

Generated long, coherent audio-visual dialogues.

Achieved accurate interpretation of multimodal queries.

Enhanced multimodal fusion for seamless interactions.

Abstract

We propose MAViD, a novel Multimodal framework for Audio-Visual Dialogue understanding and generation. Existing approaches primarily focus on non-interactive systems and are limited to producing constrained and unnatural human speech. The primary challenge of this task lies in effectively integrating understanding and generation capabilities, as well as achieving seamless multimodal audio-video fusion. To solve these problems, we propose a Conductor-Creator architecture that divides the dialogue system into two primary components. The Conductor is tasked with understanding, reasoning, and generating instructions by breaking them down into motion and speech components, thereby enabling fine-grained control over interactions. The Creator then delivers interactive responses based on these instructions. Furthermore, to address the difficulty of generating long videos with consistent identity, timbre, and tone using dual DiT structures, the Creator adopts a structure that combines autoregressive (AR) and diffusion models. The AR model is responsible for audio generation, while the diffusion model ensures high-quality video generation. Additionally, we propose a novel fusion module to enhance connections between contextually consecutive clips and modalities, enabling synchronized long-duration audio-visual content generation. Extensive experiments demonstrate that our framework can generate vivid and contextually coherent long-duration dialogue interactions and accurately interpret users' multimodal queries.