English(EN) From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animation

语音表示影响3D面部动画质量

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-11 17:41

研究人员探讨了不同的语音表示如何影响3D面部动画的质量。该研究比较了四类语音表示，并使用客观和感知测量方法，通过两个面部解码器评估了它们的有效性。研究结果表明，在语音表示中编码语音类别可以更准确地预测面部动画。 AI

影响这项研究通过优化语音数据的使用，有望实现更真实、更准确的AI驱动的面部动画系统。

排序理由该集群包含一篇在arXiv上发表的研究论文，详细介绍了对用于3D面部动画的语音表示的研究。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 该集群包含一篇在arXiv上发表的研究论文，详细介绍了对用于3D面部动画的语音表示的研究。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 90 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Pedro Correa, Olivier Perrotin, Samir Sadok, Paula Costa, Thomas Hueber · 2026-06-12 04:00

从令牌到人脸：研究用于3D面部动画的离散语音表示

arXiv:2606.13630v1 Announce Type: new Abstract: The choice of speech representation is critical in speech-driven 3D facial animation. Representations differ in what they encode: SSL features emphasize segmental and semantic cues, neural codecs yield latents optimized for acoustic…
arXiv cs.CL TIER_1 English(EN) · Thomas Hueber · 2026-06-11 17:41

从令牌到人脸：研究用于3D面部动画的离散语音表示

The choice of speech representation is critical in speech-driven 3D facial animation. Representations differ in what they encode: SSL features emphasize segmental and semantic cues, neural codecs yield latents optimized for acoustic reconstruction, and ASR-style objectives produc…