Papers › LipNet: End-to-End Sentence-level Lipreading

LipNet: End-to-End Sentence-level Lipreading

5 Nov 2016arXiv:1611.01599archive 2025-07-28

Yannis M. Assael, Brendan Shillingford, Shimon Whiteson, Nando de Freitas

Lipreading is the task of decoding text from the movement of a speaker's mouth. Traditional approaches separated the problem into two stages: designing or learning visual features, and prediction. More recent deep lipreading approaches are end-to-end trainable (Wand et al., 2016; Chung & Zisserman, 2016a). However, existing work on models trained end-to-end perform only word classification, rather than sentence-level sequence prediction. Studies have shown that human lipreading performance increases for longer words (Easton & Basala, 1982), indicating the importance of features capturing temporal context in an ambiguous communication channel. Motivated by this observation, we present LipNet, a model that maps a variable-length sequence of video frames to text, making use of spatiotemporal convolutions, a recurrent network, and the connectionist temporal classification loss, trained entirely end-to-end. To the best of our knowledge, LipNet is the first end-to-end sentence-level lipreading model that simultaneously learns spatiotemporal visual features and a sequence model. On the GRID corpus, LipNet achieves 95.2% accuracy in sentence-level, overlapped speaker split task, outperforming experienced human lipreaders and the previous 86.4% word-level state-of-the-art accuracy (Gergen et al., 2016).

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 3 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 5 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 10 samples from 2 repositories, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

13 repositories listed; official and paper-mentioned ones first.

rizkiarm/LipNet officialmentioned on GitHubtfMITSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
Abishalini/LipReadingGUI mentioned on GitHubSyntology: not harvested report
Fengdalu/LipNet-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
LiZhenghua0311/lip mentioned on GitHubtfMITSyntology: not harvested report
PlatDrake2875/LipNet mentioned on GitHubpytorchMITSyntology: not harvested report
SohaibAnwaar/lip-Reading-by-Deep-learning mentioned on GitHubtfMITSyntology: not harvested report
hero9968/lipnet-python mentioned on GitHubtfMITSyntology: not harvested report
ms8909/LipONet mentioned on GitHubtfMITSyntology: not harvested report
pjenpoomjai/LipNet mentioned on GitHubtfApache-2.0Syntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
sailordiary/LipNet-PyTorch mentioned on GitHubpytorchBSD-3-ClauseSyntology: 4 samples, 1 ran (0 instrument-failed) · 3 unverified report
ski-net/lipnet mentioned on GitHubmxnetSyntology: not harvested report
speech-separation-hse/video-features mentioned on GitHubpytorchSyntology: not harvested report
PatrickPrakash/LiptoSpeech tfSyntology: not harvested 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

15 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

10ran
5unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

rizkiarm/LipNet official repository 5 samples, 3 ran (0 instrument-failed) · 2 unverified
labels_to_text lipnet/lipreading/helpers.py ran MIT (permissive) · ba5f0f129eba0ac3 · report fixture: signature labels:Tensor/1/int · returned str · level recorded 2026-09-25
text_to_labels lipnet/lipreading/helpers.py ran fingerprinted MIT (permissive) · 071ed9f14cb9d384 · report fixture: signature text:str/0/str · returned list · level recorded 2026-09-25
threadsafe_generator lipnet/helpers/threadsafe.py ran MIT (permissive) · 6656877b73807105 · report fixture: signature f:callable/0/? · returned function · level recorded 2026-09-25
ctc_lambda_func lipnet/core/loss.py unverified MIT (permissive) · 8181d94a6381a30a · report
decode in 57 papers lipnet/core/decoders.py unverified MIT (permissive) · 07d26c38ea615861 · report
pjenpoomjai/LipNet community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
get_file_extension common/files.py ran fingerprinted Apache-2.0 (permissive) · bc11ac6762ddee1c · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-26
is_dir common/files.py ran Apache-2.0 (permissive) · 0ab02e700216530c · report fixture: signature path:str/0/str · returned bool · level recorded 2026-09-26
is_file common/files.py ran Apache-2.0 (permissive) · 74ffcb74cead6878 · report fixture: signature path:str/0/str · returned bool · level recorded 2026-09-26
tokenize in 176 papers core/decoding/spell.py ran fingerprinted Apache-2.0 (permissive) · 9108c44188636656 · report fixture: signature text:str/0/str · returned list · level recorded 2026-09-26
untokenize core/decoding/spell.py ran Apache-2.0 (permissive) · 8b832c2b8bf29a51 · report fixture: signature words:list/1/str · returned str · level recorded 2026-09-26
video_to_frames core/video.py ran Apache-2.0 (permissive) · face0a3bb9c1c095 · report fixture: signature video_filename:str/0/str · returned int · level recorded 2026-09-26
sailordiary/LipNet-PyTorch community (archive-listed) 4 samples, 1 ran (0 instrument-failed) · 3 unverified
round augmentation.py ran fingerprinted BSD-3-Clause (permissive) · 6460635662358375 · report fixture: signature x:float/0/float · returned int · level recorded 2026-09-26
ctc_collate dataloader.py unverified BSD-3-Clause (permissive) · 88b8acae6777424e · report
read_data in 132 papers augmentation.py unverified BSD-3-Clause (permissive) · f3ec786915134721 · report
round dataloader.py unverified BSD-3-Clause (permissive) · 80b5790c95657203 · report

Tasks

General ClassificationLipreadingSentence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lipreading GRID corpus (mixed-speech) LipNet Word Error Rate (WER) 4.6 #5 of 5 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