JAM-Flow：基于流匹配的联合音频-运动合成

摘要

在生成建模中，面部运动与语音之间的内在联系常被忽视，其中说话头部合成与文本转语音（TTS）通常被视为独立任务。本文介绍JAM-Flow，一个统一框架，旨在同时合成并基于面部运动和语音进行条件生成。我们的方法利用流匹配技术和创新的多模态扩散变换器（MM-DiT）架构，集成了专门的运动-DiT和音频-DiT模块。这些模块通过选择性联合注意力层相连，并采用了关键架构设计，如时间对齐的位置编码和局部联合注意力掩码，以实现有效的跨模态交互，同时保留各模态的独特优势。通过以修复式目标进行训练，JAM-Flow支持广泛的输入条件——包括文本、参考音频和参考运动——在单一连贯的模型中，促进了从文本生成同步说话头部、音频驱动动画等多种任务。JAM-Flow通过提供整体音视频合成的实用解决方案，显著推进了多模态生成建模的发展。项目页面：https://joonghyuk.com/jamflow-web

English

The intrinsic link between facial motion and speech is often overlooked in generative modeling, where talking head synthesis and text-to-speech (TTS) are typically addressed as separate tasks. This paper introduces JAM-Flow, a unified framework to simultaneously synthesize and condition on both facial motion and speech. Our approach leverages flow matching and a novel Multi-Modal Diffusion Transformer (MM-DiT) architecture, integrating specialized Motion-DiT and Audio-DiT modules. These are coupled via selective joint attention layers and incorporate key architectural choices, such as temporally aligned positional embeddings and localized joint attention masking, to enable effective cross-modal interaction while preserving modality-specific strengths. Trained with an inpainting-style objective, JAM-Flow supports a wide array of conditioning inputs-including text, reference audio, and reference motion-facilitating tasks such as synchronized talking head generation from text, audio-driven animation, and much more, within a single, coherent model. JAM-Flow significantly advances multi-modal generative modeling by providing a practical solution for holistic audio-visual synthesis. project page: https://joonghyuk.com/jamflow-web

JAM-Flow：基于流匹配的联合音频-运动合成

JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching

摘要

Support