From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animation

• URL: http://arxiv.org/abs/2606.13630v1
• Date: Thu, 11 Jun 2026 17:41:18 GMT
• Title: From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animation
• Abstract summary: SSL features emphasize segmental and semantic cues, neural codecs yield latents optimized for acoustic reconstruction, and ASR-style objectives produce label-based spaces.<n>We evaluate four speech representation families for 3D facial synthesis, comparing their facial reconstruction quality across two facial decoders.<n>We introduce an Audio Visual Text-to-Speech pipeline that leverages, as a shared space, discrete representations to decode speech and 3D facial motion.
• Score: 8.213984771916182
• License: http://creativecommons.org/licenses/by/4.0/
• 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 reconstruction, and ASR-style objectives produce label-based spaces. We evaluate four speech representation families for 3D facial synthesis, comparing their facial reconstruction quality across two facial decoders using objective metrics and a perceptual evaluation. We additionally conduct probing analyses that relate tokenized representations to phonetic units and to articulatory deformations. We found that encoding phonetic classes is beneficial for accurate facial animation prediction on both semantic and label-based representations with comparable facial animation quality. From the latter, we introduce an Audio Visual Text-to-Speech (AVTTS) pipeline that leverages, as a shared space, discrete representations to decode speech and 3D facial motion.

Related papers

• VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis [70.76837748695841]
  We propose VisualSpeaker, a novel method that bridges the gap using photorealistic differentiable rendering, supervised by visual speech recognition, for improved 3D facial animation.<n>Our contribution is a perceptual lip-reading loss, derived by passing 3D Gaussian Splatting avatar renders through a pre-trained Visual Automatic Speech Recognition model during training.<n> Evaluation on the MEAD dataset demonstrates that VisualSpeaker improves both the standard Lip Vertex Error metric by 56.1% and the perceptual quality of the generated animations, while retaining the controllability of mesh-driven animation.
  arXiv  Detail & Related papers  (2025-07-08T15:04:17Z)
• GaussianSpeech: Audio-Driven Gaussian Avatars [76.10163891172192]
  We introduce GaussianSpeech, a novel approach that synthesizes high-fidelity animation sequences of photo-realistic, personalized 3D human head avatars from spoken audio.<n>We propose a compact and efficient 3DGS-based avatar representation that generates expression-dependent color and leverages wrinkle- and perceptually-based losses to synthesize facial details.
  arXiv  Detail & Related papers  (2024-11-27T18:54:08Z)
• Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation [41.489700112318864]
  Speech-driven 3D facial animation aims to synthesize vivid facial animations that accurately synchronize with speech and match the unique speaking style. We introduce an innovative speaking style disentanglement method, which enables arbitrary-subject speaking style encoding. We also propose a novel framework called textbfMimic to learn disentangled representations of the speaking style and content from facial motions.
  arXiv  Detail & Related papers  (2023-12-18T01:49:42Z)
• Personalized Speech-driven Expressive 3D Facial Animation Synthesis with Style Control [1.8540152959438578]
  A realistic facial animation system should consider such identity-specific speaking styles and facial idiosyncrasies to achieve high-degree of naturalness and plausibility. We present a speech-driven expressive 3D facial animation synthesis framework that models identity specific facial motion as latent representations (called as styles) Our framework is trained in an end-to-end fashion and has a non-autoregressive encoder-decoder architecture with three main components.
  arXiv  Detail & Related papers  (2023-10-25T21:22:28Z)
• DF-3DFace: One-to-Many Speech Synchronized 3D Face Animation with Diffusion [68.85904927374165]
  We propose DF-3DFace, a diffusion-driven speech-to-3D face mesh synthesis. It captures the complex one-to-many relationships between speech and 3D face based on diffusion. It simultaneously achieves more realistic facial animation than the state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-08-23T04:14:55Z)
• FaceXHuBERT: Text-less Speech-driven E(X)pressive 3D Facial Animation Synthesis Using Self-Supervised Speech Representation Learning [0.0]
  FaceXHuBERT is a text-less speech-driven 3D facial animation generation method. It is very robust to background noise and can handle audio recorded in a variety of situations. It produces superior results with respect to the realism of the animation 78% of the time.
  arXiv  Detail & Related papers  (2023-03-09T17:05:19Z)
• Pose-Controllable 3D Facial Animation Synthesis using Hierarchical Audio-Vertex Attention [52.63080543011595]
  A novel pose-controllable 3D facial animation synthesis method is proposed by utilizing hierarchical audio-vertex attention. The proposed method can produce more realistic facial expressions and head posture movements.
  arXiv  Detail & Related papers  (2023-02-24T09:36:31Z)
• Imitator: Personalized Speech-driven 3D Facial Animation [63.57811510502906]
  State-of-the-art methods deform the face topology of the target actor to sync the input audio without considering the identity-specific speaking style and facial idiosyncrasies of the target actor. We present Imitator, a speech-driven facial expression synthesis method, which learns identity-specific details from a short input video. We show that our approach produces temporally coherent facial expressions from input audio while preserving the speaking style of the target actors.
  arXiv  Detail & Related papers  (2022-12-30T19:00:02Z)
• Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation [28.157431757281692]
  We propose a text-based talking-head video generation framework that synthesizes high-fidelity facial expressions and head motions. Our framework consists of a speaker-independent stage and a speaker-specific stage. Our algorithm achieves high-quality photo-realistic talking-head videos including various facial expressions and head motions according to speech rhythms.
  arXiv  Detail & Related papers  (2021-04-16T09:44:12Z)
• Audio- and Gaze-driven Facial Animation of Codec Avatars [149.0094713268313]
  We describe the first approach to animate Codec Avatars in real-time using audio and/or eye tracking. Our goal is to display expressive conversations between individuals that exhibit important social signals.
  arXiv  Detail & Related papers  (2020-08-11T22:28:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.