mlsanityData to 14 Oct 2026

PESTalk: Speech-Driven 3D Facial Animation with Personalized Emotional Styles

arXiv 2512.05121 ↗First posted 13 Oct 2025cs.GR cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

PESTalk is a novel method for generating 3D facial animations with personalized emotional styles directly from speech. It overcomes key limitations of existing approaches by introducing a Dual-Stream Emotion Extractor (DSEE) that captures both time and frequency-domain audio features for fine-grained emotion analysis, and an Emotional Style Modeling Module (ESMM) that models individual expression patterns based on voiceprint characteristics. To address data scarcity, the method leverages a newly constructed 3D-EmoStyle dataset. Evaluations demonstrate that PESTalk outperforms state-of-the-art methods in producing realistic and personalized facial animations.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 23 of its 40 references that are in the map. First posted on arXiv 13 Oct 2025.

Builds on

23 of 40 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,103
  4. 2019MediaPipe: A Framework for Building Perception Pipelinescited by 583
  5. 2022EMOCA: Emotion Driven Monocular Face Capture and Animationcited by 255
  6. 2021FaceFormer: Speech-Driven 3D Facial Animation with Transformerscited by 209
  7. 2021MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglementcited by 190
  8. 2023CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Priorcited by 184
  9. 2023EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animationcited by 142
  10. 2023Emotional Speech-Driven Animation with Content-Emotion Disentanglementcited by 98
  11. 2023DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Modelscited by 81
  12. 2023FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusioncited by 78
11 more
  1. 2023SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Facescited by 68
  2. 2021Deep Learning for Micro-expression Recognition: A Surveycited by 43
  3. 2024MEMO: Memory-Guided Diffusion for Expressive Talking Video Generationcited by 38
  4. 2023DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face Diffusercited by 16
  5. 2023Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animationcited by 16
  6. 20213D-TalkEmo: Learning to Synthesize 3D Emotional Talking Headcited by 11
  7. 2020A Comparison of Metric Learning Loss Functions for End-To-End Speaker Verificationcited by 8
  8. 2023SAiD: Speech-driven Blendshape Facial Animation with Diffusioncited by 8
  9. 2024GLDiTalker: Speech-Driven 3D Facial Animation with Graph Latent Diffusion Transformercited by 8
  10. 2023PMMTalk: Speech-Driven 3D Facial Animation from Complementary Pseudo Multi-modal Featurescited by 6
  11. 2024PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026EditEmoTalk: Controllable Speech-Driven 3D Facial Animation with Continuous Expression Editingcited by 1
  2. 2026EmoZone-Talker: Regional Semantic Control of Audio-Driven 3DGS Talking Heads via Facial Action Unitscited by 0
  3. 2026Human4K: A Large-Scale 4K Multi-View Mocap Dataset for Whole-Body 3D Human Reconstructioncited by 0
  4. 2026PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectificationcited by 0