Papers › Deep Audio-Visual Speech Recognition
Deep Audio-Visual Speech Recognition
Triantafyllos Afouras, Joon Son Chung, Andrew Senior, Oriol Vinyals, Andrew Zisserman
The goal of this work is to recognise phrases and sentences being spoken by a talking face, with or without the audio. Unlike previous works that have focussed on recognising a limited number of words or phrases, we tackle lip reading as an open-world problem - unconstrained natural language sentences, and in the wild videos. Our key contributions are: (1) we compare two models for lip reading, one using a CTC loss, and the other using a sequence-to-sequence loss. Both models are built on top of the transformer self-attention architecture; (2) we investigate to what extent lip reading is complementary to audio speech recognition, especially when the audio signal is noisy; (3) we introduce and publicly release a new dataset for audio-visual speech recognition, LRS2-BBC, consisting of thousands of natural sentences from British television. The models that we train surpass the performance of all previous work on a lip reading benchmark dataset by a significant margin.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Audio-Visual Speech Recognition | LRS2 | TM-CTC | Test WER | 8.2 | #7 of 8 | Archive leaderboard | report |
| Audio-Visual Speech Recognition | LRS2 | TM-Seq2seq | Test WER | 8.5 | #8 of 8 | Archive leaderboard | report |
| Audio-Visual Speech Recognition | LRS3-TED | TM-seq2seq | Word Error Rate (WER) | 7.2 | #12 of 12 | Archive leaderboard | report |
| Automatic Speech Recognition (ASR) | LRS2 | TM-seq2seq | Test WER | 9.7 | #8 of 9 | Archive leaderboard | report |
| Automatic Speech Recognition (ASR) | LRS2 | TM-CTC | Test WER | 10.1 | #9 of 9 | Archive leaderboard | report |
| Lipreading | LRS2 | TM-seq2seq + extLM | Word Error Rate (WER) | 48.3 | #19 of 25 | Archive leaderboard | report |
| Lipreading | LRS2 | TM-CTC + extLM | Word Error Rate (WER) | 54.7 | #24 of 25 | Archive leaderboard | report |
| Lipreading | LRS3-TED | TM-seq2seq | Word Error Rate (WER) | 58.9 | #21 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.
Methods
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