Papers › LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild

LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild

16 Oct 2018arXiv:1810.06990archive 2025-07-28

Shuang Yang, Yuan-Hang Zhang, Dalu Feng, Mingmin Yang, Chenhao Wang, Jing-Yun Xiao, Keyu Long, Shiguang Shan, Xilin Chen

Large-scale datasets have successively proven their fundamental importance in several research fields, especially for early progress in some emerging topics. In this paper, we focus on the problem of visual speech recognition, also known as lipreading, which has received increasing interest in recent years. We present a naturally-distributed large-scale benchmark for lip reading in the wild, named LRW-1000, which contains 1,000 classes with 718,018 samples from more than 2,000 individual speakers. Each class corresponds to the syllables of a Mandarin word composed of one or several Chinese characters. To the best of our knowledge, it is currently the largest word-level lipreading dataset and also the only public large-scale Mandarin lipreading dataset. This dataset aims at covering a "natural" variability over different speech modes and imaging conditions to incorporate challenges encountered in practical applications. It has shown a large variation in this benchmark in several aspects, including the number of samples in each class, video resolution, lighting conditions, and speakers' attributes such as pose, age, gender, and make-up. Besides providing a detailed description of the dataset and its collection pipeline, we evaluate several typical popular lipreading methods and perform a thorough analysis of the results from several aspects. The results demonstrate the consistency and challenges of our dataset, which may open up some new promising directions for future work.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Fengdalu/Lipreading-DenseNet3D mentioned on GitHubpytorch report
NirHeaven/D3D mentioned on GitHubpytorch report

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 ReadingLipreadingSpeech RecognitionVisual Speech Recognitionspeech-recognition

Datasets

Introduced by this paper, per the archive.

CAS-VSR-W1k (LRW-1000)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lipreading LRW-1000 3D Conv + ResNet-34 + Bi-GRU Top-1 Accuracy 38.19% #2 of 4 Archive leaderboard report
Lipreading LRW-1000 DenseNet3D + Bi-GRU Top-1 Accuracy 34.76% #3 of 4 Archive leaderboard report
Lipreading LRW-1000 Multi-Tower LSTM-5 Top-1 Accuracy 25.76% #4 of 4 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