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

6 Mar 2020arXiv:2003.03206archive 2025-07-28

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.

PaperPDFCode

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

Lip ReadingLipreadingSentenceSpeech RecognitionVisual Speech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
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

Cutout

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