Papers › Learn an Effective Lip Reading Model without Pains
Learn an Effective Lip Reading Model without Pains
Dalu Feng, Shuang Yang, Shiguang Shan, Xilin Chen
Lip reading, also known as visual speech recognition, aims to recognize the speech content from videos by analyzing the lip dynamics. There have been several appealing progress in recent years, benefiting much from the rapidly developed deep learning techniques and the recent large-scale lip-reading datasets. Most existing methods obtained high performance by constructing a complex neural network, together with several customized training strategies which were always given in a very brief description or even shown only in the source code. We find that making proper use of these strategies could always bring exciting improvements without changing much of the model. Considering the non-negligible effects of these strategies and the existing tough status to train an effective lip reading model, we perform a comprehensive quantitative study and comparative analysis, for the first time, to show the effects of several different choices for lip reading. By only introducing some easy-to-get refinements to the baseline pipeline, we obtain an obvious improvement of the performance from 83.7% to 88.4% and from 38.2% to 55.7% on two largest public available lip reading datasets, LRW and LRW-1000, respectively. They are comparable and even surpass the existing state-of-the-art results.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Lipreading | CAS-VSR-W1k (LRW-1000) | 3D-ResNet + Bi-GRU + MixUp + Label Smooth + Cosine LR (Word Boundary) | Top-1 Accuracy | 55.7% | #2 of 9 | Archive leaderboard | report |
| Lipreading | CAS-VSR-W1k (LRW-1000) | 3D-ResNet + Bi-GRU + MixUp + Label Smooth + Cosine LR | Top-1 Accuracy | 48.3% | #5 of 9 | Archive leaderboard | report |
| Lipreading | Lip Reading in the Wild | 3D-ResNet + Bi-GRU + MixUp + Label Smoothing + Cosine LR (Word Boundary) | Top-1 Accuracy | 88.4 | #9 of 22 | Archive leaderboard | report |
| Lipreading | Lip Reading in the Wild | 3D-ResNet + Bi-GRU + MixUp + Label Smoothing + Cosine LR | Top-1 Accuracy | 85.5 | #10 of 22 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections