Research map / Vision-language and multimodal / Human and embodied modeling
V2C: Visual Voice Cloning
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use V2C-Net instead of FastSpeech2 | Speech synthesis on V2C-Animation · V2C-Animation | MCD: 12.08 -> 11.79 | Helped |
| Use V2C-Net instead of FastSpeech2 | Speech synthesis on V2C-Animation · V2C-Animation | MCD-DTW-SL: 10.31 -> 10.05 | Helped |
| Use V2C-Net instead of FastSpeech2 | Speech synthesis on V2C-Animation · V2C-Animation | Id. Acc.: 59.38 -> 62.50 | Helped |
| Use V2C-Net instead of FastSpeech2 | Speech synthesis on V2C-Animation · V2C-Animation | Emo. Acc.: 53.13 -> 56.25 | Helped |
| Use V2C-Net instead of FastSpeech2 | Speech synthesis on V2C-Animation · V2C-Animation | MOS-naturalness: 3.86 $\pm$ 0.07 -> 3.97 $\pm$ 0.06 | Helped |
| Use V2C-Net instead of FastSpeech2 | Speech synthesis on V2C-Animation · V2C-Animation | MOS-similarity: 3.75 $\pm$ 0.06 -> 3.90 $\pm$ 0.06 | Helped |
| Add reference video emotion input (ablation) | V2C-Net with reference audio · V2C-Animation | Id. Acc.: 59.38 -> 62.50 | Helped |
| Add reference video emotion input (ablation) | V2C-Net with reference audio · V2C-Animation | Emo. Acc.: 53.13 -> 56.25 | Helped |
| Add reference audio speaker input (ablation) | V2C-Net with reference video · V2C-Animation | Id. Acc.: 25.00 -> 62.50 | Helped |
| Add reference audio speaker input (ablation) | V2C-Net with reference video · V2C-Animation | Emo. Acc.: 47.61 -> 56.25 | Helped |
| Add video embedding as an input to SV2TTS | SV2TTS on V2C-Animation · V2C-Animation | Emo. Acc.: 37.19 -> 41.24 | Helped |
| Use V2C-Animation rather than Multi-speaker for SV2TTS | SV2TTS · Multi-speaker vs. V2C-Animation | MCD: 12.37 -> 21.08 | Hurt |
Closest papers by meaning
- RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (NeurIPS 2026 · similarity 0.87)
- Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement (ICLR 2025 · similarity 0.85)
- AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation (CVPR 2024 · similarity 0.85)
- EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing (CVPR 2025 · similarity 0.85)
- From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech (CVPR 2025 · similarity 0.85)
- Tell What You Hear From What You See - Video to Audio Generation Through Text (NeurIPS 2024 · similarity 0.84)
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.