Research map / Video / Video generation
Neural Dubber: Dubbing for Videos According to Scripts
Chenxu Hu, Qiao Tian, Tingle Li, Wang Yuping, Yuxuan Wang, Hang Zhao
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 |
|---|---|---|---|
| Condition speech generation on video with the text-video aligner | Neural Dubber versus FastSpeech 2 · chem test | AV Sync MOS: 3.29 -> 3.91 | Improved |
| Condition speech generation on video with the text-video aligner | Neural Dubber versus FastSpeech 2 · chem test | LSE-D: 11.86 -> 7.212 | Improved |
| Condition speech generation on video with the text-video aligner | Neural Dubber versus FastSpeech 2 · chem test | Audio Quality MOS: 3.71 -> 3.74 | No clear effect |
| Use Neural Dubber instead of Video-based Tacotron | Video-based Tacotron · chem test | AV Sync MOS: 3.03 -> 3.91 | Improved |
| Use Neural Dubber instead of FastSpeech 2 | FastSpeech 2 · LRS2 test | Audio Quality MOS: 3.15 -> 3.58 | Improved |
| Use Neural Dubber instead of FastSpeech 2 | FastSpeech 2 · LRS2 test | AV Sync MOS: 3.33 -> 3.62 | Improved |
| Use Neural Dubber instead of FastSpeech 2 | FastSpeech 2 · LRS2 test | LSE-D: 10.17 -> 7.201 | Improved |
| Use Neural Dubber instead of Lip2Wav | Lip2Wav · chem test | STOI: 0.282 -> 0.467 | Improved |
| Use Neural Dubber instead of Lip2Wav | Lip2Wav · chem test | WER: 72.70% -> 18.01% | Improved |
| Use Neural Dubber instead of Lip2Wav | Lip2Wav · chem test | PESQ: 1.194 -> 1.250 | Improved |
Closest papers by meaning
- Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing (CVPR 2025 · similarity 0.88)
- EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing (CVPR 2025 · similarity 0.87)
- MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis (CVPR 2025 · similarity 0.85)
- Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement (ICLR 2025 · similarity 0.85)
- TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation (NeurIPS 2025 · similarity 0.85)
- NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers (ICLR 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.
