{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:26Z","timestamp":1761894686147,"version":"build-2065373602"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210123","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["CrossMuSim: A Cross-Modal Framework for Music Similarity Retrieval with LLM-Powered Text Description Sourcing and Mining"],"prefix":"10.1109","author":[{"given":"Tristan","family":"Tsoi","sequence":"first","affiliation":[{"name":"Huawei Technologies,Audio Lab Hong Kong, Hong Kong Research Center,Hong Kong SAR"}]},{"given":"Jiajun","family":"Deng","sequence":"additional","affiliation":[{"name":"Huawei Technologies,Audio Lab Hong Kong, Hong Kong Research Center,Hong Kong SAR"}]},{"given":"Yaolong","family":"Ju","sequence":"additional","affiliation":[{"name":"Huawei Technologies,Audio Lab Hong Kong, Hong Kong Research Center,Hong Kong SAR"}]},{"given":"Benno","family":"Weck","sequence":"additional","affiliation":[{"name":"Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain"}]},{"given":"Holger","family":"Kirchhoff","sequence":"additional","affiliation":[{"name":"Huawei Technologies,Munich Research Center,Munich,Germany"}]},{"given":"Simon","family":"Lui","sequence":"additional","affiliation":[{"name":"Huawei Technologies,Audio Lab Hong Kong, Hong Kong Research Center,Hong Kong SAR"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3478847"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1101826.1101840"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053442"},{"article-title":"Musical audio similarity with self-supervised convolutional neural networks","year":"2022","author":"Thom\u00e9","key":"ref4"},{"key":"ref5","article-title":"Representation learning of music using artist labels","author":"Park","year":"2018","journal-title":"Int. Society for Music Information Retrieval (ISMIR)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.913750"},{"volume-title":"and Thomas Sikora, MPEG-7 audio and beyond: Audio content indexing and retrieval","year":"2006","author":"Kim","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/09298210802479284"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-61520-919-4.ch014"},{"key":"ref10","article-title":"Five approaches to collecting tags for music","author":"Turnbull","year":"2008","journal-title":"Int. Society for Music Information Retrieval (ISMIR)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/11735106_58"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2011.1"},{"key":"ref13","article-title":"Improvements of audio-based music similarity and genre classificaton","author":"Pampalk","year":"2005","journal-title":"Int. Society for Music Information Retrieval (ISMIR)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2001.1237829"},{"key":"ref15","article-title":"Audio content-based music retrieval","author":"Grosche","year":"2012","journal-title":"Dagstuhl Follow-Ups (DFU)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413711"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952130"},{"article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Int. Conf. on Machine Learning (ICML)","author":"Chen","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094670"},{"key":"ref20","article-title":"Mu-Lan: A joint embedding of music audio and natural language","author":"Huang","year":"2022","journal-title":"Int. Society for Music Information Retrieval (ISMIR)"},{"key":"ref21","article-title":"Contrastive audio-language learning for music","author":"Manco","year":"2022","journal-title":"Int. Society for Music Information Retrieval (ISMIR)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56435-2_4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746996"},{"article-title":"MusicLM: Generating music from text","year":"2023","author":"Agostinelli","key":"ref24"},{"article-title":"Fast timing-conditioned latent audio diffusion","year":"2024","author":"Evans","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref27","article-title":"Lp-musiccaps: Llm-based pseudo music captioning","author":"Doh","year":"2023","journal-title":"Int. Society for Music Information Retrieval (ISMIR)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.27"},{"key":"ref29","article-title":"Augment, drop & swap: Improving diversity in llm captions for efficient music-text representation learning","author":"Manco","year":"2024","journal-title":"Int. Society for Music Information Retrieval (ISMIR)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"ref32","article-title":"Semi-supervised music tagging transformer","author":"Won","year":"2021","journal-title":"Int. Society for Music Information Retrieval (ISMIR)"},{"key":"ref33","article-title":"The million song dataset","author":"Bertin-Mahieux","year":"2011","journal-title":"Int. Society for Music Information Retrieval (ISMIR)"},{"key":"ref34","article-title":"Improved deep metric learning with multi-class n-pair loss objective","author":"Sohn","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref35","article-title":"Contrastive learning of musical representations","author":"Spijkervet","year":"2021","journal-title":"Int. Society for Music Information Retrieval (ISMIR)"},{"article-title":"MERT: Acoustic music understanding model with large-scale self-supervised training","volume-title":"Int. Conf. on Learning Representations (ICLR)","author":"Li","key":"ref36"},{"article-title":"MuChin: A chinese colloquial description benchmark for evaluating language models in the field of music","volume-title":"Int. Joint Conf. on Artificial Intelligence (ICJAI)","author":"Wang","key":"ref37"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210123.pdf?arnumber=11210123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:32Z","timestamp":1761888812000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210123\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210123","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}