{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/auto-avsr-audio-visual-speech-recognition","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","arxiv_id":"2303.14307","date":"2023-03-25","proceeding":null,"authors":["Pingchuan Ma","Alexandros Haliassos","Adriana Fernandez-Lopez","Honglie Chen","Stavros Petridis","Maja Pantic"],"abstract":"Audio-visual speech recognition has received a lot of attention due to its robustness against acoustic noise. Recently, the performance of automatic, visual, and audio-visual speech recognition (ASR, VSR, and AV-ASR, respectively) has been substantially improved, mainly due to the use of larger models and training sets. However, accurate labelling of datasets is time-consuming and expensive. Hence, in this work, we investigate the use of automatically-generated transcriptions of unlabelled datasets to increase the training set size. For this purpose, we use publicly-available pre-trained ASR models to automatically transcribe unlabelled datasets such as AVSpeech and VoxCeleb2. Then, we train ASR, VSR and AV-ASR models on the augmented training set, which consists of the LRS2 and LRS3 datasets as well as the additional automatically-transcribed data. We demonstrate that increasing the size of the training set, a recent trend in the literature, leads to reduced WER despite using noisy transcriptions. The proposed model achieves new state-of-the-art performance on AV-ASR on LRS2 and LRS3. In particular, it achieves a WER of 0.9% on LRS3, a relative improvement of 30% over the current state-of-the-art approach, and outperforms methods that have been trained on non-publicly available datasets with 26 times more training data.","url_abs":"https://arxiv.org/abs/2303.14307v3","url_pdf":"https://arxiv.org/pdf/2303.14307v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"auto-avsr-audio-visual-speech-recognition","repo_url":"https://github.com/mpc001/auto_avsr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"auto-avsr-audio-visual-speech-recognition","repo_url":"https://github.com/umbertocappellazzo/llama-avsr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"audio-visual-speech-recognition","task_name":"Audio-Visual Speech Recognition"},{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"lipreading","task_name":"Lipreading"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"visual-speech-recognition","task_name":"Visual Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-visual-speech-recognition-on-lrs2","task":"Audio-Visual Speech Recognition","dataset":"LRS2","model":"CTC/Attention","rank_in_archive_order":2,"of":8,"metrics":{"Test WER":"1.5"},"uses_additional_data":true},{"leaderboard":"/sota/audio-visual-speech-recognition-on-lrs3-ted","task":"Audio-Visual Speech Recognition","dataset":"LRS3-TED","model":"CTC/Attention","rank_in_archive_order":4,"of":12,"metrics":{"Word Error Rate (WER)":"0.9"},"uses_additional_data":true},{"leaderboard":"/sota/automatic-speech-recognition-on-lrs2","task":"Automatic Speech Recognition (ASR)","dataset":"LRS2","model":"CTC/Attention","rank_in_archive_order":2,"of":9,"metrics":{"Test WER":"1.5"},"uses_additional_data":true},{"leaderboard":"/sota/automatic-speech-recognition-asr-on-lrs3-ted","task":"Automatic Speech Recognition (ASR)","dataset":"LRS3-TED","model":"CTC/Attention","rank_in_archive_order":2,"of":2,"metrics":{"Word Error Rate (WER)":"1"},"uses_additional_data":false},{"leaderboard":"/sota/lipreading-on-lrs2","task":"Lipreading","dataset":"LRS2","model":"Auto-AVSR","rank_in_archive_order":1,"of":25,"metrics":{"Word Error Rate (WER)":"14.6"},"uses_additional_data":true},{"leaderboard":"/sota/lipreading-on-lrs3-ted","task":"Lipreading","dataset":"LRS3-TED","model":"Auto-AVSR","rank_in_archive_order":2,"of":23,"metrics":{"Word Error Rate (WER)":"19.1"},"uses_additional_data":true},{"leaderboard":"/sota/visual-speech-recognition-on-lrs3-ted","task":"Visual Speech Recognition","dataset":"LRS3-TED","model":"CTC/Attention","rank_in_archive_order":1,"of":3,"metrics":{"Word Error Rate (WER)":"19.1"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.14307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14307"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mpc001/auto_avsr","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/umbertocappellazzo/llama-avsr","reach":{"status":"ok"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3ae2eab75af094e1","entry":"average_checkpoints","repo":"mpc001/auto_avsr","repo_kind":"official","path":"average_checkpoints.py","file_url":"https://github.com/mpc001/auto_avsr/blob/HEAD/average_checkpoints.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ae2eab75af094e1"}},{"code_sha256_prefix":"0a672d203cd8007f","entry":"collate_pad","repo":"mpc001/auto_avsr","repo_kind":"official","path":"datamodule/data_module.py","file_url":"https://github.com/mpc001/auto_avsr/blob/HEAD/datamodule/data_module.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0a672d203cd8007f"}},{"code_sha256_prefix":"41d108cb26723328","entry":"end_detect","repo":"mpc001/auto_avsr","repo_kind":"official","path":"espnet/nets/e2e_asr_common.py","file_url":"https://github.com/mpc001/auto_avsr/blob/HEAD/espnet/nets/e2e_asr_common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"41d108cb26723328"}},{"code_sha256_prefix":"eddc218242d34add","entry":"ensemble","repo":"mpc001/auto_avsr","repo_kind":"official","path":"average_checkpoints.py","file_url":"https://github.com/mpc001/auto_avsr/blob/HEAD/average_checkpoints.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eddc218242d34add"}},{"code_sha256_prefix":"e3ffd0b6ffbdf70f","entry":"load_video","repo":"mpc001/auto_avsr","repo_kind":"official","path":"datamodule/av_dataset.py","file_url":"https://github.com/mpc001/auto_avsr/blob/HEAD/datamodule/av_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e3ffd0b6ffbdf70f"}},{"code_sha256_prefix":"593d603cc0b0a93f","entry":"pad","repo":"mpc001/auto_avsr","repo_kind":"official","path":"datamodule/data_module.py","file_url":"https://github.com/mpc001/auto_avsr/blob/HEAD/datamodule/data_module.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"593d603cc0b0a93f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}