{"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":"/code/load-audio-visual","entry":"load_audio_visual","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":5,"n_papers_ran":0,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":3,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":3},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2602.21646","paper":"/paper/arxiv-2602-21646","title":"Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"yxduir/LLM-SRT","path":"SLAM-LLM/src/slam_llm/datasets/avhubert_dataset.py","file_url":"https://github.com/yxduir/LLM-SRT/blob/HEAD/SLAM-LLM/src/slam_llm/datasets/avhubert_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f0641584d0fe0fb5","mcp_get_code":{"code_sha256":"f0641584d0fe0fb5"}},{"arxiv_id":"2407.03563","paper":"/paper/learning-video-temporal-dynamics-with-cross","title":"Learning Video Temporal Dynamics with Cross-Modal Attention for Robust Audio-Visual Speech Recognition","date":"2024-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sungnyun/avsr-temporal-dynamics","path":"avhubert/hubert_dataset.py","file_url":"https://github.com/sungnyun/avsr-temporal-dynamics/blob/HEAD/avhubert/hubert_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f0641584d0fe0fb5","mcp_get_code":{"code_sha256":"f0641584d0fe0fb5"}},{"arxiv_id":"2402.15151","paper":"/paper/where-visual-speech-meets-language-vsp-llm","title":"Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sally-sh/vsp-llm","path":"src/hubert_dataset.py","file_url":"https://github.com/sally-sh/vsp-llm/blob/HEAD/src/hubert_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f0641584d0fe0fb5","mcp_get_code":{"code_sha256":"f0641584d0fe0fb5"}},{"arxiv_id":"2402.15151","paper":"/paper/where-visual-speech-meets-language-vsp-llm","title":"Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sally-sh/vsp-llm","path":"src/vsp_llm_dataset.py","file_url":"https://github.com/sally-sh/vsp-llm/blob/HEAD/src/vsp_llm_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"c9b8148d516d0989","mcp_get_code":{"code_sha256":"c9b8148d516d0989"}},{"arxiv_id":"2401.03468","paper":"/paper/multichannel-av-wav2vec2-a-framework-for","title":"Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation","date":"2024-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zqs01/multi-channel-wav2vec2","path":"avhubert/hubert_dataset.py","file_url":"https://github.com/zqs01/multi-channel-wav2vec2/blob/HEAD/avhubert/hubert_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2c590c63adc5c7ef","mcp_get_code":{"code_sha256":"2c590c63adc5c7ef"}},{"arxiv_id":"2312.02512","paper":"/paper/av2av-direct-audio-visual-speech-to-audio","title":"AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation","date":"2023-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"choijeongsoo/av2av","path":"av2unit/avhubert/hubert_dataset.py","file_url":"https://github.com/choijeongsoo/av2av/blob/HEAD/av2unit/avhubert/hubert_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f0641584d0fe0fb5","mcp_get_code":{"code_sha256":"f0641584d0fe0fb5"}}]}