SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.06112 · ICCV · 2023

Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping

Merouane Debbah, Sanath Narayan, Yasser Abdelaziz, Dahou Djilali, Haithem Boussaid, Ebtessam Almazrouei

arXiv · PDF · Open in the Atlas

Code that ran

17 of 19 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 6 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 10 failures of our instrument; 2 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2308.06112.json · badge: /api/ran/2308.06112.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
YasserdahouML/Lip2Vec canonical (classifier label)
classifier basis: census
17 ran · 2 no recorded run
FunctionStatusWhere it lives
apply_transform Ran
ran; our contract draft was wrong, not the code
YasserdahouML/Lip2Vec/datasets/preprocess.py
pointer only (licence: NONE) · get_code("362b232acbc220b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

crop Ran
ran; our contract draft was wrong, not the code
YasserdahouML/Lip2Vec/datasets/functional_video.py
pointer only (licence: NONE) · get_code("c6fb86dd68007249")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

exact_div Ran
ran, honoured the contract we drafted
YasserdahouML/Lip2Vec/datasets/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from qwenlm/qwen-audio, is pointer only (licence: NOASSERTION) · get_code("6e0808fc4828513a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_cer Ran
ran, honoured the contract we drafted
YasserdahouML/Lip2Vec/metrics/measures.py
pointer only (licence: NONE) · get_code("5fcb88dca39140d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_er Ran
ran, honoured the contract we drafted
YasserdahouML/Lip2Vec/metrics/measures.py
pointer only (licence: NONE); the stored copy get_code serves, from ahaliassos/usr, is pointer only (licence: NONE) · get_code("f646df9b796b4337")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_video_properties Ran
ran; our contract draft was wrong, not the code
YasserdahouML/Lip2Vec/datasets/utils_data.py
pointer only (licence: NONE) · get_code("8b03deae3bdc3ad3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_wer Ran
ran, honoured the contract we drafted
YasserdahouML/Lip2Vec/metrics/measures.py
pointer only (licence: NONE); the stored copy get_code serves, from ahaliassos/usr, is pointer only (licence: NONE) · get_code("f0ad236b3b39fdaf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

linear_interpolate Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
YasserdahouML/Lip2Vec/datasets/preprocess.py
pointer only (licence: NONE) · get_code("5fc5cf4404249a10")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_audio Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
YasserdahouML/Lip2Vec/datasets/utils_data.py
pointer only (licence: NONE) · get_code("b3510aa8b8ed8518")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

optional_int Ran
ran, honoured the contract we drafted
YasserdahouML/Lip2Vec/datasets/utils.py
pointer only (licence: NONE) · get_code("e56996b20b9c19cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pad_or_trim Ran
ran; our contract draft was wrong, not the code
YasserdahouML/Lip2Vec/datasets/audio.py
pointer only (licence: NONE) · get_code("9f13de1c23e4003d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_txt_lines Ran
ran; our contract draft was wrong, not the code
YasserdahouML/Lip2Vec/datasets/utils_data.py
pointer only (licence: NONE) · get_code("8c9319bbaa8f67c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

resize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
YasserdahouML/Lip2Vec/datasets/functional_video.py
pointer only (licence: NONE) · get_code("a42f16eadfb7718f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

resized_crop Ran
ran; our contract draft was wrong, not the code
YasserdahouML/Lip2Vec/datasets/functional_video.py
pointer only (licence: NONE) · get_code("b0239305ba36c73f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sinusoids Ran
ran, honoured the contract we drafted
YasserdahouML/Lip2Vec/models/prior.py
pointer only (licence: NONE) · get_code("a314b3fcba001058")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

str2bool Ran
ran, violated the contract we drafted
YasserdahouML/Lip2Vec/datasets/utils.py
pointer only (licence: NONE) · get_code("176b6ba6c2c2940c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

warp_img Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
YasserdahouML/Lip2Vec/datasets/preprocess.py
pointer only (licence: NONE) · get_code("353e88e37719cd08")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_transformer Not yet run
unverified (harvested, no recorded run)
YasserdahouML/Lip2Vec/models/transformer.py
pointer only (licence: NONE) · get_code("5c86d34cae9ef6a1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

mel_filters Not yet run
unverified (harvested, no recorded run)
YasserdahouML/Lip2Vec/datasets/audio.py
pointer only (licence: NONE) · get_code("edf924293b4b2375")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, YasserdahouML/Lip2Vec when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 10 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 1 the same month, 8 later) and 9 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
sinusoids 9 other papers
3 dated earlier, 6 later
2212.04356 (2022-12)
Robust Speech Recognition via Large-Scale Weak Supervision
2306.05284 (2023-06)
Simple and Controllable Music Generation
2307.03183 (2023-07)
Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers
and 6 more not named here
exact_div 6 other papers
2 dated earlier, 4 later
2212.04356 (2022-12)
Robust Speech Recognition via Large-Scale Weak Supervision
2306.01428 (2023-06)
Improved DeepFake Detection Using Whisper Features
2309.15701 (2023-09)
HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models
and 3 more not named here
pad_or_trim 5 other papers
1 dated earlier, 4 later
2212.04356 (2022-12)
Robust Speech Recognition via Large-Scale Weak Supervision
2406.10082 (2024-06)
Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation
2506.08967 (2025-06)
Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
and 2 more not named here
optional_int 4 other papers
1 dated earlier, 3 later
2212.04356 (2022-12)
Robust Speech Recognition via Large-Scale Weak Supervision
2309.15701 (2023-09)
HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models
2406.10082 (2024-06)
Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation
and 1 more not named here
str2bool 4 other papers
1 dated earlier, 3 later
2212.04356 (2022-12)
Robust Speech Recognition via Large-Scale Weak Supervision
2309.15701 (2023-09)
HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models
2406.10082 (2024-06)
Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation
and 1 more not named here
get_er 2 other papers
2 later
2404.02098 (2024-04)
BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory Speech Recognition
2411.02256 (2024-11)
Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs
get_wer 2 other papers
2 later
2404.02098 (2024-04)
BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory Speech Recognition
2411.02256 (2024-11)
Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs
mel_filters 2 other papers
1 dated earlier, 1 later
2212.04356 (2022-12)
Robust Speech Recognition via Large-Scale Weak Supervision
2506.08967 (2025-06)
Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
crop 1 other paper
1 dated earlier
136670659 (2022 (year only))
MovieCuts: A New Dataset and Benchmark for Cut Type Recognition
linear_interpolate 1 other paper
1 the same month
2308.08143 (2023-08)
IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Visual Speech Recognition (VSR) differs from the common perception tasks as it requires deeper reasoning over the video sequence, even by human experts. Despite the recent advances in VSR, current approaches rely on labeled data to fully train or finetune their models predicting the target speech. This hinders their ability to generalize well beyond the training set and leads to performance degeneration under out-of-distribution challenging scenarios. Unlike previous works that involve auxiliary losses or complex training procedures and architectures, we propose a simple approach, named Lip2Vec that is based on learning a prior model. Given a robust visual speech encoder, this network maps the encoded latent representations of the lip sequence to their corresponding latents from the audio pair, which are sufficiently invariant for effective text decoding. The generated audio representation is then decoded to text using an off-the-shelf Audio Speech Recognition (ASR) model. The proposed model compares favorably with fullysupervised learning methods on the LRS3 dataset achieving 26 WER. Unlike SoTA approaches, our model keeps a reasonable performance on the VoxCeleb2-en test set. We believe that reprogramming the VSR as an ASR task narrows the performance gap between the two and paves the way for more flexible formulations of lip reading.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2308.06112")
get_code_for_paper("2308.06112")
have("2308.06112")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2308.06112.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2308.06112.svg)](https://syntology.ai/paper/2308.06112)

Connect an agent — have() is free.