Research map / Image generation / Autoregressive and latent generation
MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation
Sungwoo Cho, Jeongsoo Choi, Sungnyun Kim, Se-Young Yun
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 visual guidance to audio guidance (ablation) | MAVFlow · CREMA-D | Emo-Acc (%): 35.85 -> 36.46 | Improved |
| add visual guidance to audio guidance (ablation) | MAVFlow · MuAViC | speaker similarity: 0.487 -> 0.504 | Improved |
| add visual guidance to audio guidance (ablation) | MAVFlow · MuAViC | MCD-DTW: 7.50 -> 7.37 | Improved |
| add audio guidance (x-vector) to no guidance (ablation) | MAVFlow · CREMA-D | speaker similarity: 0.167 -> 0.391 | Improved |
| add audio guidance to no guidance (ablation) | MAVFlow · MuAViC | speaker similarity: 0.057 -> 0.487 | Improved |
| add visual guidance alone without audio (ablation) | MAVFlow · CREMA-D | Emo-Acc (%): 28.66 -> 26.83 | Hurt |
| add visual guidance alone without audio (ablation) | MAVFlow · CREMA-D | speaker similarity: 0.167 -> 0.174 | No clear effect |
| replace AV2AV renderer with CFM-based MAVFlow | AV2AV · CREMA-D | Emo-Acc (%): 33.66 -> 36.46 | Improved |
| replace AV2AV renderer with MAVFlow | AV2AV · MuAViC Fr-En | speaker similarity: 0.31 -> 0.51 | Improved |
| replace AV2AV renderer with MAVFlow | AV2AV · MuAViC It-En | MCD-DTW-SL: 14.75 -> 11.43 | Improved |
| replace AV2AV renderer with MAVFlow | AV2AV · MuAViC Es-En | ASR-BLEU: 26.57 -> 26.97 | Improved |
| replace AV2AV renderer with MAVFlow | AV2AV · MuAViC | MOS naturalness: 3.58 -> 4.01 | Improved |
Closest papers by meaning
- AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation (CVPR 2024 · similarity 0.89)
- StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching (AAAI 2025 · similarity 0.88)
- From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech (CVPR 2025 · similarity 0.86)
- Enhancing Zero-Shot Multi-Speaker TTS with Negated Speaker Representations (AAAI 2024 · similarity 0.85)
- Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement (ICLR 2025 · similarity 0.85)
- Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows (CVPR 2025 · similarity 0.85)
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.
