Research map / Video / Video generation
EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents
Yu Zhang, Kaiyuan Shen, Yang Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add LS-state conditioning to the input (ablation) | EmbodiedHead · Ablation: listening-speaking module | MOD: 2.43 -> 2.10 | Improved |
| add FiLM modulation of cross-attention on top of LS-state (ablation) | EmbodiedHead · Ablation: listening-speaking module | MOD: 2.10 -> 1.99 | Improved |
| add reference and audio embeddings to AdaLN global condition (ablation) | EmbodiedHead · Ablation: global condition | LVE: 6.20 -> 5.76 | Improved |
| add motion magnitude condition alone (ablation) | EmbodiedHead · Ablation: global condition | LVE: 5.97 -> 6.20 | Hurt |
| add second-stage image-domain joint fine-tuning with renderer (ablation) | EmbodiedHead · EmbodiedHead speaking test set | PSNR: 17.53 -> 18.28 | Improved |
| add second-stage image-domain fine-tuning (ablation) | EmbodiedHead · EmbodiedHead speaking test set | LVE: 5.70 -> 5.71 | No clear effect |
| increase sampling steps from 4 to 25 (ablation) | EmbodiedHead · Ablation: inference steps | LVE: 5.76 -> 6.18 | Hurt |
| increase sampling steps from 1 to 25 (ablation) | EmbodiedHead · Ablation: inference steps | FDD: 1.76 -> 1.44 | Improved |
| use single-stream audio with LS-state instead of dual-stream audio | EmbodiedHead · DualTalk test set | LVE: 7.94 -> 7.18 | Improved |
| use single-stream audio instead of dual-stream audio | EmbodiedHead · DualTalk test set | BA: 0.42 -> 0.39 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FaceFormer — FaceFormer: Speech-Driven 3D Facial Animation With Transformers (CVPR 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations (CVPR 2025 · similarity 0.88)
- DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation (ICLR 2025 · similarity 0.88)
- Teller: Real-Time Streaming Audio-Driven Portrait Animation with Autoregressive Motion Generation (CVPR 2025 · similarity 0.88)
- VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time (NeurIPS 2024 · similarity 0.87)
- Diffusion-based Realistic Listening Head Generation via Hybrid Motion Modeling (CVPR 2025 · similarity 0.87)
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
