{"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/toward-universal-text-to-music-retrieval","title":"Toward Universal Text-to-Music Retrieval","arxiv_id":"2211.14558","date":"2022-11-26","proceeding":null,"authors":["Seungheon Doh","Minz Won","Keunwoo Choi","Juhan Nam"],"abstract":"This paper introduces effective design choices for text-to-music retrieval systems. An ideal text-based retrieval system would support various input queries such as pre-defined tags, unseen tags, and sentence-level descriptions. In reality, most previous works mainly focused on a single query type (tag or sentence) which may not generalize to another input type. Hence, we review recent text-based music retrieval systems using our proposed benchmark in two main aspects: input text representation and training objectives. Our findings enable a universal text-to-music retrieval system that achieves comparable retrieval performances in both tag- and sentence-level inputs. Furthermore, the proposed multimodal representation generalizes to 9 different downstream music classification tasks. We present the code and demo online.","url_abs":"https://arxiv.org/abs/2211.14558v1","url_pdf":"https://arxiv.org/pdf/2211.14558v1.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":"toward-universal-text-to-music-retrieval","repo_url":"https://github.com/seungheondoh/msd-subsets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"toward-universal-text-to-music-retrieval","repo_url":"https://github.com/seungheondoh/music-text-representation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"toward-universal-text-to-music-retrieval","repo_url":"https://github.com/seungheondoh/msu-benchmark","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"music-classification","task_name":"Music Classification"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.14558","atlas_url":"https://app.syntology.ai/?focus=2211.14558","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}