Research map / Image generation / Editing and style transfer
Talking Face Generation With Multilingual TTS
Read the paperCheck 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 the proposed talking-face model instead of Wav2Lip for out-of-training-language speech | Talking face generation · Non-English and other out-of-training-language speech | cross-language lip-motion robustness | Helped |
| Use the proposed talking-face model instead of Wav2Lip | Talking face generation · Compared output image sequences | visual image quality | Helped |
| Add adversarial training with a multi-scale discriminator | Talking face generation model · Generated face images | perceptual visual quality | Helped |
| Inject language embeddings into the text encoder and duration predictor | Multilingual VITS · Multilingual speech synthesis | speech synthesis quality | Helped |
| Feed the speaker embedding directly to the duration predictor | Multilingual VITS · Cross-lingual speech synthesis | speech quality | Hurt |
Closest papers by meaning
- Faces that Speak: Jointly Synthesising Talking Face and Speech from Text (CVPR 2024 · similarity 0.86)
- VQTalker: Towards Multilingual Talking Avatars Through Facial Motion Tokenization (AAAI 2025 · similarity 0.82)
- FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of Different Styles (AAAI 2025 · similarity 0.80)
- Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation (CVPR 2025 · similarity 0.79)
- MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes (NeurIPS 2024 · similarity 0.79)
- FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization (CVPR 2024 · similarity 0.79)
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.