{"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/lp-musiccaps-llm-based-pseudo-music","title":"LP-MusicCaps: LLM-Based Pseudo Music Captioning","arxiv_id":"2307.16372","date":"2023-07-31","proceeding":null,"authors":["Seungheon Doh","Keunwoo Choi","Jongpil Lee","Juhan Nam"],"abstract":"Automatic music captioning, which generates natural language descriptions for given music tracks, holds significant potential for enhancing the understanding and organization of large volumes of musical data. Despite its importance, researchers face challenges due to the costly and time-consuming collection process of existing music-language datasets, which are limited in size. To address this data scarcity issue, we propose the use of large language models (LLMs) to artificially generate the description sentences from large-scale tag datasets. This results in approximately 2.2M captions paired with 0.5M audio clips. We term it Large Language Model based Pseudo music caption dataset, shortly, LP-MusicCaps. We conduct a systemic evaluation of the large-scale music captioning dataset with various quantitative evaluation metrics used in the field of natural language processing as well as human evaluation. In addition, we trained a transformer-based music captioning model with the dataset and evaluated it under zero-shot and transfer-learning settings. The results demonstrate that our proposed approach outperforms the supervised baseline model.","url_abs":"https://arxiv.org/abs/2307.16372v1","url_pdf":"https://arxiv.org/pdf/2307.16372v1.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":"lp-musiccaps-llm-based-pseudo-music","repo_url":"https://github.com/seungheondoh/lp-music-caps","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"lp-musiccaps-llm-based-pseudo-music","repo_url":"https://github.com/MindSpore-scientific-2/code-8/tree/main/text-to-music","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"music-captioning","task_name":"Music Captioning"},{"task_slug":"tag","task_name":"TAG"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2307.16372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.16372"}},"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/MindSpore-scientific-2/code-8/tree/main/text-to-music","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seungheondoh/lp-music-caps","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1},"listed":{"samples":3,"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":4,"samples":[{"code_sha256_prefix":"bd3578806ecf5ac2","entry":"adjust_learning_rate","repo":"seungheondoh/lp-music-caps","repo_kind":"official","path":"lpmc/music_captioning/transfer.py","file_url":"https://github.com/seungheondoh/lp-music-caps/blob/HEAD/lpmc/music_captioning/transfer.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bd3578806ecf5ac2"}},{"code_sha256_prefix":"af8afe1f9058dbc1","entry":"ms","repo":"seungheondoh/lp-music-caps","repo_kind":"official","path":"demo/utils/audio_utils.py","file_url":"https://github.com/seungheondoh/lp-music-caps/blob/HEAD/demo/utils/audio_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"af8afe1f9058dbc1"}},{"code_sha256_prefix":"da903d73dd3b59c1","entry":"normalize","repo":"seungheondoh/lp-music-caps","repo_kind":"official","path":"demo/utils/audio_utils.py","file_url":"https://github.com/seungheondoh/lp-music-caps/blob/HEAD/demo/utils/audio_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"da903d73dd3b59c1"}},{"code_sha256_prefix":"e04a7c27c2fe82f7","entry":"sinusoids","repo":"seungheondoh/lp-music-caps","repo_kind":"official","path":"lpmc/music_captioning/model/modules.py","file_url":"https://github.com/seungheondoh/lp-music-caps/blob/HEAD/lpmc/music_captioning/model/modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e04a7c27c2fe82f7"}},{"code_sha256_prefix":"16298c972234921e","entry":"generate_sample","repo":"MindSpore-scientific-2/code-8","repo_kind":"listed","path":"QuantExplainNLP_AlgoAnalysis/data_preprocessing.py","file_url":"https://github.com/MindSpore-scientific-2/code-8/blob/HEAD/QuantExplainNLP_AlgoAnalysis/data_preprocessing.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":"16298c972234921e"}},{"code_sha256_prefix":"5919a74fc358ee01","entry":"get_feature_names","repo":"MindSpore-scientific-2/code-8","repo_kind":"listed","path":"QuantExplainNLP_AlgoAnalysis/explainability.py","file_url":"https://github.com/MindSpore-scientific-2/code-8/blob/HEAD/QuantExplainNLP_AlgoAnalysis/explainability.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":"5919a74fc358ee01"}},{"code_sha256_prefix":"ef93260b5137f73b","entry":"maybe_num_nodes","repo":"MindSpore-scientific-2/code-8","repo_kind":"listed","path":"RGNN/model_simple.py","file_url":"https://github.com/MindSpore-scientific-2/code-8/blob/HEAD/RGNN/model_simple.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":"ef93260b5137f73b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}