Research map / Vision-language and multimodal / Cross-modal learning
LinProVSR: Linguistics-Knowledge Guided Progressive Disambiguation Network for Visual Speech Recognition
Feng Xue, Baochao Zhu, Wei Jia, Shujie Li, Yu Li, Jinrui Zhang, Shengeng Tang, Dan Guo
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 Viseme-Phoneme Disambiguation (VPD) to the base (ablation) | LinProVSR base · CMLR | WER (%): 25.90 -> 25.23 | Improved |
| add VPD to the base (ablation) | LinProVSR base · LRS2 | WER (%): 43.02 -> 36.25 | Improved |
| add Text Semantic Disambiguation (TSD) to the base (ablation) | LinProVSR base · LRS2 | WER (%): 43.02 -> 40.31 | Improved |
| add TSD to the base (ablation) | LinProVSR base · CMLR | WER (%): 25.90 -> 25.64 | Improved |
| add VPD to the base (ablation) | LinProVSR base · GRID | WER (%): 2.76 -> 1.28 | Improved |
| add TSD on top of VPD (ablation) | LinProVSR (VPD only) · CMLR | WER (%): 25.23 -> 23.34 | Improved |
| add TSD on top of VPD (ablation) | LinProVSR (VPD only) · GRID | WER (%): 1.28 -> 0.99 | Improved |
| add TSD on top of VPD (ablation) | LinProVSR (VPD only) · LRS2 | WER (%): 36.25 -> 35.36 | Improved |
Closest papers by meaning
- VALLR: Visual ASR Language Model for Lip Reading (ICCV 2025 · similarity 0.90)
- Language Without Borders: A Dataset and Benchmark for Code-Switching Lip Reading (NeurIPS 2024 · similarity 0.86)
- LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading (ICLR 2024 · similarity 0.85)
- Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling (NeurIPS 2026 · similarity 0.85)
- Personalized Lip Reading: Adapting to Your Unique Lip Movements with Vision and Language (AAAI 2025 · similarity 0.85)
- VSRo-200: A Romanian Visual Speech Recognition Dataset for Studying Supervision and Multimodal Robustness (NeurIPS 2026 · 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.
