{"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/mavl-a-multilingual-audio-video-lyrics","title":"MAVL: A Multilingual Audio-Video Lyrics Dataset for Animated Song Translation","arxiv_id":"2505.18614","date":"2025-05-24","proceeding":null,"authors":["Woohyun Cho","Youngmin Kim","Sunghyun Lee","Youngjae Yu"],"abstract":"Lyrics translation requires both accurate semantic transfer and preservation of musical rhythm, syllabic structure, and poetic style. In animated musicals, the challenge intensifies due to alignment with visual and auditory cues. We introduce Multilingual Audio-Video Lyrics Benchmark for Animated Song Translation (MAVL), the first multilingual, multimodal benchmark for singable lyrics translation. By integrating text, audio, and video, MAVL enables richer and more expressive translations than text-only approaches. Building on this, we propose Syllable-Constrained Audio-Video LLM with Chain-of-Thought SylAVL-CoT, which leverages audio-video cues and enforces syllabic constraints to produce natural-sounding lyrics. Experimental results demonstrate that SylAVL-CoT significantly outperforms text-based models in singability and contextual accuracy, emphasizing the value of multimodal, multilingual approaches for lyrics translation.","url_abs":"https://arxiv.org/abs/2505.18614v2","url_pdf":"https://arxiv.org/pdf/2505.18614v2.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":"mavl-a-multilingual-audio-video-lyrics","repo_url":"https://github.com/k1064190/MAVL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"rhythm","task_name":"Rhythm"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"mavl","method_name":"MAVL"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.18614","atlas_url":"https://app.syntology.ai/?focus=2505.18614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18614"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/jianfch/stable-ts","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":13,"unverified":6},"by_repo_kind":{"found_in_text":{"samples":19,"ran":13,"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":"edd87e3d5219c886","entry":"as_vanilla","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/whisper_compatibility.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/whisper_compatibility.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":"edd87e3d5219c886"}},{"code_sha256_prefix":"a2906ebf1c03e2b2","entry":"dfnet_audio","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/audio/dfnet.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/audio/dfnet.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":"a2906ebf1c03e2b2"}},{"code_sha256_prefix":"f0b041c207e1f563","entry":"encode_video_comparison","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/video_output.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/video_output.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":"f0b041c207e1f563"}},{"code_sha256_prefix":"88205be653cfa848","entry":"finalize_text","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/text_output.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/text_output.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":"88205be653cfa848"}},{"code_sha256_prefix":"2f71dfac10f2811e","entry":"get_func_parameters","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/utils.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/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":"2f71dfac10f2811e"}},{"code_sha256_prefix":"8c364004420fb08f","entry":"get_val","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/default.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/default.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":"8c364004420fb08f"}},{"code_sha256_prefix":"2cb0d3956bd3ca79","entry":"has_key","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/default.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/default.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":"2cb0d3956bd3ca79"}},{"code_sha256_prefix":"9595a2a36e654ced","entry":"isolate_useful_options","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/utils.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/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":"9595a2a36e654ced"}},{"code_sha256_prefix":"1385e684ee00e274","entry":"sec2hhmmss","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/text_output.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/text_output.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":"1385e684ee00e274"}},{"code_sha256_prefix":"940741f0689b881e","entry":"sec2milliseconds","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/text_output.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/text_output.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":"940741f0689b881e"}},{"code_sha256_prefix":"6e5e6a677cc59eed","entry":"set_get_val","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/default.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/default.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":"6e5e6a677cc59eed"}},{"code_sha256_prefix":"fa9a731acd304668","entry":"split_word_tokens","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/timing.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/timing.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":"fa9a731acd304668"}},{"code_sha256_prefix":"0c886f090ffcc1ab","entry":"str_to_valid_type","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/utils.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/utils.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":"0c886f090ffcc1ab"}},{"code_sha256_prefix":"7b13c54749fcc4a8","entry":"find_alignment_stable","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/timing.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/timing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b13c54749fcc4a8"}},{"code_sha256_prefix":"50582ac3612eaa85","entry":"get_alignment_tokenizer","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/alignment.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/alignment.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50582ac3612eaa85"}},{"code_sha256_prefix":"8eb94fa43ead16a2","entry":"get_tokenizer","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/whisper_compatibility.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/whisper_compatibility.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8eb94fa43ead16a2"}},{"code_sha256_prefix":"52e3fba663460cae","entry":"get_valid_language","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/whisper_compatibility.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/whisper_compatibility.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52e3fba663460cae"}},{"code_sha256_prefix":"4a82dc494d002e7f","entry":"load_dfnet_model","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/audio/dfnet.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/audio/dfnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4a82dc494d002e7f"}},{"code_sha256_prefix":"4d0397204f102619","entry":"pop_empty_alignment","repo":"jianfch/stable-ts","repo_kind":"found_in_text","path":"stable_whisper/timing.py","file_url":"https://github.com/jianfch/stable-ts/blob/HEAD/stable_whisper/timing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d0397204f102619"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}