Papers › Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition
Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition
Yuan-Hang Zhang, Shuang Yang, Jing-Yun Xiao, Shiguang Shan, Xilin Chen
Recent advances in deep learning have heightened interest among researchers in the field of visual speech recognition (VSR). Currently, most existing methods equate VSR with automatic lip reading, which attempts to recognise speech by analysing lip motion. However, human experience and psychological studies suggest that we do not always fix our gaze at each other's lips during a face-to-face conversation, but rather scan the whole face repetitively. This inspires us to revisit a fundamental yet somehow overlooked problem: can VSR models benefit from reading extraoral facial regions, i.e. beyond the lips? In this paper, we perform a comprehensive study to evaluate the effects of different facial regions with state-of-the-art VSR models, including the mouth, the whole face, the upper face, and even the cheeks. Experiments are conducted on both word-level and sentence-level benchmarks with different characteristics. We find that despite the complex variations of the data, incorporating information from extraoral facial regions, even the upper face, consistently benefits VSR performance. Furthermore, we introduce a simple yet effective method based on Cutout to learn more discriminative features for face-based VSR, hoping to maximise the utility of information encoded in different facial regions. Our experiments show obvious improvements over existing state-of-the-art methods that use only the lip region as inputs, a result we believe would probably provide the VSR community with some new and exciting insights.
In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.
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 Conv + ResNet-18 + Bi-GRU (Face Cutout) | Top-1 Accuracy | 45.24% | #6 of 9 | Archive leaderboard | report |
| Lipreading | GRID corpus (mixed-speech) | LipNet (with Face Cutout) | Word Error Rate (WER) | 2.9 | #3 of 5 | Archive leaderboard | report |
| Lipreading | Lip Reading in the Wild | 3D Conv + ResNet-18 + Bi-GRU(Face Cutout) | Top-1 Accuracy | 85.02 | #13 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.
Methods
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