{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T19:30:38Z","timestamp":1774121438288,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446380","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"826-830","source":"Crossref","is-referenced-by-count":8,"title":["Enriching Music Descriptions with A Finetuned-LLM and Metadata for Text-to-Music Retrieval"],"prefix":"10.1109","author":[{"given":"SeungHeon","family":"Doh","sequence":"first","affiliation":[{"name":"KAIST,Graduate School of Culture Technology,South Korea"}]},{"given":"Minhee","family":"Lee","sequence":"additional","affiliation":[{"name":"Sogang University,Department of Computer Science and Engineering,South Korea"}]},{"given":"Dasaem","family":"Jeong","sequence":"additional","affiliation":[{"name":"Sogang University,Department of Art & Technology,South Korea"}]},{"given":"Juhan","family":"Nam","sequence":"additional","affiliation":[{"name":"KAIST,Graduate School of Culture Technology,South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.913750"},{"key":"ref2","article-title":"Zero-shot learning for audio-based music classification and tagging","volume-title":"ISMIR","author":"Choi"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413514"},{"key":"ref4","article-title":"Contrastive audio-language learning for music","volume-title":"ISMIR","author":"Manco"},{"key":"ref5","article-title":"MuLan: A joint embedding of music audio and natural language","volume-title":"ISMIR","author":"Huang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094670"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56435-2_4"},{"key":"ref8","article-title":"CLaMP: Contrastive language-music pre-training for crossmodal symbolic music information retrieval","volume-title":"ISMIR","author":"Wu"},{"key":"ref9","article-title":"MT3: Multi-task multitrack music transcription","volume-title":"ICLR","author":"Gardner"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref11","article-title":"LP-MusicCaps: Llm-based pseudo music captioning","volume-title":"ISMIR","author":"Doh"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01420"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"key":"ref14","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref15","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref16","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref17","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref18","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref20","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref21","article-title":"Bertscore: Evaluating text generation with bert","volume-title":"ICLR","author":"Zhang"},{"key":"ref22","article-title":"Artist similarity with graph neural networks","volume-title":"ISMIR","author":"Korzeniowski"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094617"},{"key":"ref24","article-title":"The 2014 labrosa audio fingerprint system","volume-title":"ISMIR","author":"Ellis"},{"key":"ref25","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref26","article-title":"The song describer dataset: a corpus of audio captions for music-and-language evaluation","volume-title":"NeurIPS ML4Audio Workshop","author":"Manco"},{"key":"ref27","article-title":"The million song dataset","volume-title":"ISMIR","author":"Bertin-Mahieux"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref29","article-title":"Noise2music: Text-conditioned music generation with diffusion models","author":"Huang","year":"2023"},{"key":"ref30","article-title":"Fma: A dataset for music analysis","volume-title":"ISMIR","author":"Defferrard"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IWSSIP48289.2020.9145170"},{"key":"ref32","article-title":"Listen, read, and identify: multimodal singing language identification of music","volume-title":"ISMIR","author":"Choi"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053442"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref35","article-title":"Contrastive learning for cross-modal artist retrieval","author":"Ferraro","year":"2023"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446380.pdf?arnumber=10446380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:37:04Z","timestamp":1722573424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446380","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}