Papers › Jointly Learning Visual and Auditory Speech Representations from Raw Data

Jointly Learning Visual and Auditory Speech Representations from Raw Data

12 Dec 2022arXiv:2212.06246archive 2025-07-28

Alexandros Haliassos, Pingchuan Ma, Rodrigo Mira, Stavros Petridis, Maja Pantic

We present RAVEn, a self-supervised multi-modal approach to jointly learn visual and auditory speech representations. Our pre-training objective involves encoding masked inputs, and then predicting contextualised targets generated by slowly-evolving momentum encoders. Driven by the inherent differences between video and audio, our design is asymmetric w.r.t. the two modalities' pretext tasks: Whereas the auditory stream predicts both the visual and auditory targets, the visual one predicts only the auditory targets. We observe strong results in low- and high-resource labelled data settings when fine-tuning the visual and auditory encoders resulting from a single pre-training stage, in which the encoders are jointly trained. Notably, RAVEn surpasses all self-supervised methods on visual speech recognition (VSR) on LRS3, and combining RAVEn with self-training using only 30 hours of labelled data even outperforms a recent semi-supervised method trained on 90,000 hours of non-public data. At the same time, we achieve state-of-the-art results in the LRS3 low-resource setting for auditory speech recognition (as well as for VSR). Our findings point to the viability of learning powerful speech representations entirely from raw video and audio, i.e., without relying on handcrafted features. Code and models are available at https://github.com/ahaliassos/raven.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

ahaliassos/raven officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory Speech Recognition (arXiv:2404.02098; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 5 honoured, 3 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Audio-Visual Speech RecognitionLipreadingSpeech RecognitionVisual Speech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Audio-Visual Speech Recognition LRS3-TED RAVEn Large Word Error Rate (WER) 1.4 #7 of 12 Archive leaderboard report
Lipreading LRS2 RAVEn Large Word Error Rate (WER) 18.6 #4 of 25 Archive leaderboard report
Lipreading LRS3-TED RAVEn Large Word Error Rate (WER) 23.4 #6 of 23 Archive leaderboard report
Speech Recognition LRS2 RAVEn Large Word Error Rate (WER) 2.1 #1 of 1 Archive leaderboard report
Speech Recognition LRS3-TED RAVEn Large Word Error Rate (WER) 1.4 #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