Research map / Vision-language and multimodal / Cross-modal learning
Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers
Ya Zhao, Rui Xu, Xinchao Wang, Peng Hou, Haihong Tang, Mingli Song
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 |
|---|---|---|---|
| Distill speech-recognizer knowledge at sequence, context, and frame levels | WAS lip reader · CMLR | CER: 38.93% -> 31.27% | Improved |
| Distill speech-recognizer knowledge at sequence, context, and frame levels | WAS lip reader · LRS2 | CER: 48.28% -> 45.53% | Improved |
| Add sequence-level distillation (ablation) | WAS lip reader · CMLR | CER: 38.93% -> 34.42% | Improved |
| Add context-level distillation (ablation) | WAS lip reader · CMLR | CER: 38.93% -> 33.17% | Improved |
| Add frame-level distillation (ablation) | WAS lip reader · CMLR | CER: 38.93% -> 35.30% | Improved |
| Add sequence- and context-level distillation (ablation) | WAS lip reader · CMLR | CER: 38.93% -> 32.95% | Improved |
| Add frame-level distillation to sequence- and context-level distillation (ablation) | WAS lip reader · CMLR | CER: 32.95% -> 31.27% | Improved |
| Add sequence-level distillation (ablation) | WAS lip reader · LRS2 | CER: 48.28% -> 46.04% | Improved |
| Add context-level distillation (ablation) | WAS lip reader · LRS2 | CER: 48.28% -> 46.01% | Improved |
| Add frame-level distillation (ablation) | WAS lip reader · LRS2 | CER: 48.28% -> 46.91% | Improved |
| Add sequence- and context-level distillation (ablation) | WAS lip reader · LRS2 | CER: 48.28% -> 45.97% | Improved |
| Add frame-level distillation to sequence- and context-level distillation (ablation) | WAS lip reader · LRS2 | CER: 45.97% -> 45.53% | Improved |
Closest papers by meaning
- Sub-Word Level Lip Reading With Visual Attention (CVPR 2022 · similarity 0.93)
- LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading (ICLR 2024 · similarity 0.91)
- Personalized Lip Reading: Adapting to Your Unique Lip Movements with Vision and Language (AAAI 2025 · similarity 0.91)
- Language Without Borders: A Dataset and Benchmark for Code-Switching Lip Reading (NeurIPS 2024 · similarity 0.89)
- MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading (AAAI 2025 · similarity 0.87)
- Let There Be Sound: Reconstructing High Quality Speech from Silent Videos (AAAI 2024 · similarity 0.86)
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.
