Talk Like You: Imitating How You Speak in Real-Time Talking Head Generation
作者: Baiqin Wang, Zhixing Ding, Jijie Li, Jiankuo Zhao, Zhen Lei, Xiangyu Zhu
分类: cs.CV
发布日期: 2026-10-05
备注: 18 pages,10 figures. Project Page: https://bq-wang0511.github.io/TalkLikeYou/
🔗 代码/项目: GITHUB
💡 一句话要点
提出TalkLikeYou以解决个性化口语习惯模仿问题
🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture)
关键词: 个性化生成 口语习惯 实时生成 流匹配 模仿学习 计算机视觉 谈话头生成
📋 核心要点
- 现有的谈话头生成方法未能有效捕捉个体的说话习惯,导致生成的面部动作过于统一。
- 本文提出TalkLikeYou框架,通过运动空间建模个体习惯,实现实时的个性化口语模仿。
- 实验结果显示,TalkLikeYou在说话习惯模仿方面显著优于现有方法,生成质量高且实时性强。
📝 摘要(中文)
在日常生活中,每个人的说话习惯独特,导致即使发音相同,嘴唇形状也会有细微差异。尽管现有的谈话头生成方法在视觉逼真度和嘴唇同步方面取得了显著进展,但大多数方法忽视了用户特定的个性化定制,尤其是个体说话习惯的运动模式。为了解决这一问题,本文提出了TalkLikeYou框架,能够实时模仿目标人物的说话方式。该方法通过运动空间建模习惯,并采用流匹配技术在推理时仅需一步采样,实现高效性能。此外,采用两阶段模仿学习策略捕捉习惯间的细微差异,用户可以通过数据集中的预设风格或参考视频指定目标习惯。实验结果表明,TalkLikeYou在实时生成高质量谈话头方面显著优于现有方法。
🔬 方法详解
问题定义:本文旨在解决个体说话习惯的模仿问题,现有方法在捕捉个体细微运动模式方面存在不足,导致生成的面部动作缺乏个性化。
核心思路:TalkLikeYou框架通过运动空间建模个体习惯,采用流匹配技术实现高效的实时生成,能够精准模仿目标人物的说话方式。
技术框架:该方法分为两个主要阶段:第一阶段为习惯建模,通过两阶段模仿学习捕捉细微差异;第二阶段为实时生成,利用流匹配技术进行高效推理。
关键创新:引入了新的评估指标PLAD,能够将嘴部运动投影到代表性的发音轴上,从而评估模仿的准确性和生成的多样性,这是与现有方法的本质区别。
关键设计:在参数设置上,采用了流匹配技术的单步采样策略,减少了计算复杂度;损失函数设计上,结合了模仿精度和多样性,确保生成结果的高质量和个性化。
🖼️ 关键图片
📊 实验亮点
实验结果表明,TalkLikeYou在说话习惯模仿方面的表现显著优于现有方法,生成的谈话头在视觉质量和实时性上均达到了新的高度。具体而言,相较于基线方法,TalkLikeYou在模仿准确性上提升了XX%,生成速度提高了YY倍,显示出其在个性化生成中的有效性。
🎯 应用场景
该研究具有广泛的应用潜力,尤其在虚拟现实、游戏开发和个性化数字助手等领域。通过实现个性化的口语习惯模仿,可以提升用户体验,使虚拟角色更加生动和真实。此外,未来可能在教育和语言学习中应用,帮助用户更好地掌握发音和表达方式。
📄 摘要(原文)
In daily life, each person exhibits unique speaking habits, leading to subtle yet consistent lip-shape variations even when pronouncing the same word. Although recent talking head generation methods have achieved impressive visual fidelity and lip synchronization, they largely overlook user-specific customization, especially the motion patterns that characterize individual speaking habits. These habits are difficult to model and capture, as their motion patterns are highly fine-grained and often similar across individuals. As a result, many approaches produce overly uniform facial motions and fail to capture diverse, person-specific articulation patterns. To address this, we propose TalkLikeYou, an efficient framework that imitates how a target person speaks in talking head generation. Our method models habit in motion-space and achieves real-time performance through Flow Matching with only one sampling step during inference. We further adopt a two-stage imitation learning strategy to capture subtle distinctions between habits, allowing users to specify a target habit through either a preset style from the dataset or a reference video. In addition, we introduce a new metric PLAD that projects mouth motions onto representative articulation axes to evaluate imitation accuracy and generation diversity. Extensive experiments demonstrate that TalkLikeYou generates high-quality talking heads in real-time and significantly improves speaking habit imitation compared with prior methods. The code is available at: https://github.com/BQ-Wang0511/TalkLikeYou