{"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/mixspeech-cross-modality-self-learning-with","title":"MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition","arxiv_id":"2303.05309","date":"2023-03-09","proceeding":"ICCV 2023 1","authors":["Xize Cheng","Linjun Li","Tao Jin","Rongjie Huang","Wang Lin","Zehan Wang","Huangdai Liu","Ye Wang","Aoxiong Yin","Zhou Zhao"],"abstract":"Multi-media communications facilitate global interaction among people. However, despite researchers exploring cross-lingual translation techniques such as machine translation and audio speech translation to overcome language barriers, there is still a shortage of cross-lingual studies on visual speech. This lack of research is mainly due to the absence of datasets containing visual speech and translated text pairs. In this paper, we present \\textbf{AVMuST-TED}, the first dataset for \\textbf{A}udio-\\textbf{V}isual \\textbf{Mu}ltilingual \\textbf{S}peech \\textbf{T}ranslation, derived from \\textbf{TED} talks. Nonetheless, visual speech is not as distinguishable as audio speech, making it difficult to develop a mapping from source speech phonemes to the target language text. To address this issue, we propose MixSpeech, a cross-modality self-learning framework that utilizes audio speech to regularize the training of visual speech tasks. To further minimize the cross-modality gap and its impact on knowledge transfer, we suggest adopting mixed speech, which is created by interpolating audio and visual streams, along with a curriculum learning strategy to adjust the mixing ratio as needed. MixSpeech enhances speech translation in noisy environments, improving BLEU scores for four languages on AVMuST-TED by +1.4 to +4.2. Moreover, it achieves state-of-the-art performance in lip reading on CMLR (11.1\\%), LRS2 (25.5\\%), and LRS3 (28.0\\%).","url_abs":"https://arxiv.org/abs/2303.05309v1","url_pdf":"https://arxiv.org/pdf/2303.05309v1.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":"mixspeech-cross-modality-self-learning-with","repo_url":"https://github.com/exgc/avmust-ted","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mixspeech-cross-modality-self-learning-with","repo_url":"https://github.com/rongjiehuang/transpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"lip-reading","task_name":"Lip Reading"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"self-learning","task_name":"Self-Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"visual-speech-recognition","task_name":"Visual Speech Recognition"}],"methods":[{"method_slug":"self-learning","method_name":"Self-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.05309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05309"}},"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/exgc/avmust-ted","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rongjiehuang/transpeech","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Exgc/AVMuST-TED","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7},"by_repo_kind":{"listed":{"samples":7,"ran":7,"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":"7137577cbef51217","entry":"discriminator_loss","repo":"rongjiehuang/transpeech","repo_kind":"listed","path":"research/TranSpeech/hifigan/models.py","file_url":"https://github.com/rongjiehuang/transpeech/blob/HEAD/research/TranSpeech/hifigan/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7137577cbef51217"}},{"code_sha256_prefix":"5961cc3df73025cb","entry":"extract_audio_for_eval","repo":"rongjiehuang/transpeech","repo_kind":"listed","path":"research/TranSpeech/asr_bleu/compute_asr_bleu.py","file_url":"https://github.com/rongjiehuang/transpeech/blob/HEAD/research/TranSpeech/asr_bleu/compute_asr_bleu.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5961cc3df73025cb"}},{"code_sha256_prefix":"e453b51f0ed5fb28","entry":"feature_loss","repo":"rongjiehuang/transpeech","repo_kind":"listed","path":"research/TranSpeech/hifigan/models.py","file_url":"https://github.com/rongjiehuang/transpeech/blob/HEAD/research/TranSpeech/hifigan/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e453b51f0ed5fb28"}},{"code_sha256_prefix":"1a9d74439d969cfd","entry":"generator_loss","repo":"rongjiehuang/transpeech","repo_kind":"listed","path":"research/TranSpeech/hifigan/models.py","file_url":"https://github.com/rongjiehuang/transpeech/blob/HEAD/research/TranSpeech/hifigan/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a9d74439d969cfd"}},{"code_sha256_prefix":"dddc74f9be0a9b20","entry":"merge_tailo_init_final","repo":"rongjiehuang/transpeech","repo_kind":"listed","path":"research/TranSpeech/asr_bleu/compute_asr_bleu.py","file_url":"https://github.com/rongjiehuang/transpeech/blob/HEAD/research/TranSpeech/asr_bleu/compute_asr_bleu.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dddc74f9be0a9b20"}},{"code_sha256_prefix":"fce0a244cd01d4fd","entry":"remove_tone","repo":"rongjiehuang/transpeech","repo_kind":"listed","path":"research/TranSpeech/asr_bleu/compute_asr_bleu.py","file_url":"https://github.com/rongjiehuang/transpeech/blob/HEAD/research/TranSpeech/asr_bleu/compute_asr_bleu.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fce0a244cd01d4fd"}},{"code_sha256_prefix":"d538507264c24d0b","entry":"retrieve_asr_config","repo":"rongjiehuang/transpeech","repo_kind":"listed","path":"research/TranSpeech/asr_bleu/utils.py","file_url":"https://github.com/rongjiehuang/transpeech/blob/HEAD/research/TranSpeech/asr_bleu/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d538507264c24d0b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}