Papers › Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware...

Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing

23 Feb 2024arXiv:2402.15151archive 2025-07-28

Jeong Hun Yeo, Seunghee Han, Minsu Kim, Yong Man Ro

In visual speech processing, context modeling capability is one of the most important requirements due to the ambiguous nature of lip movements. For example, homophenes, words that share identical lip movements but produce different sounds, can be distinguished by considering the context. In this paper, we propose a novel framework, namely Visual Speech Processing incorporated with LLMs (VSP-LLM), to maximize the context modeling ability by bringing the overwhelming power of LLMs. Specifically, VSP-LLM is designed to perform multi-tasks of visual speech recognition and translation, where the given instructions control the type of task. The input video is mapped to the input latent space of an LLM by employing a self-supervised visual speech model. Focused on the fact that there is redundant information in input frames, we propose a novel deduplication method that reduces the embedded visual features by employing visual speech units. Through the proposed deduplication and Low Rank Adaptation (LoRA), VSP-LLM can be trained in a computationally efficient manner. In the translation dataset, the MuAViC benchmark, we demonstrate that VSP-LLM trained on just 30 hours of labeled data can more effectively translate lip movements compared to the recent model trained with 433 hours of data.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.15151")

Code

Syntology Ran 8 of 12 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

sally-sh/vsp-llm officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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

12 samples harvested; 8 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
5ran
4unverified

Licence: 12 of the 12 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 sally-sh/vsp-llm. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

Embedding sally-sh/vsp-llm/src/vsp_llm.py official repository ran · our draft was wrong no licence file found · pointer only · 96cbb5e9ca5b6be0 · report
Linear sally-sh/vsp-llm/src/vsp_llm.py official repository ran · our draft was wrong no licence file found · pointer only · 8cd8cb0d1e9e63e4 · report
compute_mask_indices sally-sh/vsp-llm/src/utils_vsp_llm.py official repository ran no licence file found · pointer only · 581de97f5d5aa97a · report
conv3x3 sally-sh/vsp-llm/src/resnet.py official repository ran · our draft was wrong no licence file found · pointer only · 583f9780bdd00a45 · report
downsample_basic_block sally-sh/vsp-llm/src/resnet.py official repository ran no licence file found · pointer only · d50e3a8f0b0f9a21 · report
downsample_basic_block_v2 sally-sh/vsp-llm/src/resnet.py official repository ran no licence file found · pointer only · 546a770034e200d1 · report
find_runs sally-sh/vsp-llm/src/utils_vsp_llm.py official repository ran no licence file found · pointer only · db4a33e22cd9f644 · report
load_video sally-sh/vsp-llm/src/utils_vsp_llm.py official repository ran no licence file found · pointer only · d5a7afb95212031e · report
load_audio_visual sally-sh/vsp-llm/src/hubert_dataset.py official repository unverified no licence file found · pointer only · f0641584d0fe0fb5 · report
load_audio_visual sally-sh/vsp-llm/src/vsp_llm_dataset.py official repository unverified licence not identified · pointer only · c9b8148d516d0989 · report
load_label sally-sh/vsp-llm/src/vsp_llm_dataset.py official repository unverified no licence file found · pointer only · 113a523619225ba0 · report
load_label_offset sally-sh/vsp-llm/src/vsp_llm_dataset.py official repository unverified no licence file found · pointer only · 3e9450b6ac2fcddd · report

Tasks

Lip ReadingLipreadingSpeech RecognitionTranslationVisual Speech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lipreading LRS3-TED VSP-LLM Word Error Rate (WER) 25.4 #7 of 23 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