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

arXiv: https://arxiv.org/abs/2606.13630 · HTML: https://mlsanity.com/paper/2606.13630/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 11 Jun 2026.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [FaceFormer: Speech-Driven 3D Facial Animation with Transformers](https://mlsanity.com/paper/2112.05329/) (2021)
- [MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement](https://mlsanity.com/paper/2104.08223/) (2021)
- [CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior](https://mlsanity.com/paper/2301.02379/) (2023)
- [EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation](https://mlsanity.com/paper/2303.11089/) (2023)
- [WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling](https://mlsanity.com/paper/2408.16532/) (2024)
- [EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling](https://mlsanity.com/paper/2401.00374/) (2023)
- [FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusion](https://mlsanity.com/paper/2309.11306/) (2023)
- [BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec](https://mlsanity.com/paper/2409.05377/) (2024)
- [SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters](https://mlsanity.com/paper/2412.00174/) (2024)
- [ProbTalk3D: Non-Deterministic Emotion Controllable Speech-Driven 3D Facial Animation Synthesis Using VQ-VAE](https://mlsanity.com/paper/2409.07966/) (2024)
- [VQTalker: Towards Multilingual Talking Avatars through Facial Motion Tokenization](https://mlsanity.com/paper/2412.09892/) (2024)
- [Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Heads](https://mlsanity.com/paper/2410.11041/) (2024)
- [Bringing Interpretability to Neural Audio Codecs](https://mlsanity.com/paper/2506.04492/) (2025)

## Built on by (most cited first, 1 of 1)

- [EMODY Flow: Emotion-Aware Audio-Driven Full-Body Motion Generation](https://mlsanity.com/paper/2609.16011/) (2026)

## Abstract (arXiv)

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.