{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:33:37Z","timestamp":1776890017369,"version":"3.51.2"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11231012","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Temporal Adaptation of Pre-trained Foundation Models for Music Structure Analysis"],"prefix":"10.1109","author":[{"given":"Yixiao","family":"Zhang","sequence":"first","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haonan","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ju-Chiang","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jitong","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/12513.001.0001"},{"key":"ref2","article-title":"Learning hierarchical metrical structure beyond measures","volume-title":"Ismir 2022 Hybrid Conference","author":"Jiang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/09298210701653344"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853980"},{"key":"ref5","first-page":"255","article-title":"Joint beat and downbeat tracking with recurrent neural networks","volume-title":"ISMIR","author":"B\u00f6ck"},{"key":"ref6","article-title":"Using pairwise link prediction and graph attention networks for music structure analysis","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Buisson"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.869637"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.910781"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637644"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853679"},{"key":"ref11","first-page":"417","article-title":"Boundary detection in music structure analysis using convolutional neural networks","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Ullrich"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413773"},{"key":"ref13","first-page":"730","article-title":"Supervised metric learning for music structure features","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Wang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747252"},{"key":"ref15","article-title":"Learning multi-level representations for hierarchical music structure analysis","volume-title":"International Society for Music Information Retrieval Conference Conference (ISMIR)","author":"Buisson"},{"key":"ref16","article-title":"MIREX 2013: Structural segmentation","year":"2013"},{"key":"ref17","article-title":"A meta-analysis of the mirex structure segmentation task","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Smith"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.78"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683492"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461319"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/9781119890980"},{"key":"ref22","first-page":"625","article-title":"State of the art report: Audio-based music structure analysis","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Paulus"},{"key":"ref23","article-title":"MERT: acoustic music understanding model with large-scale self-supervised training","volume-title":"The Twelfth International Conference on Learning Representations ICLR","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448314"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3602320"},{"key":"ref26","article-title":"Foundation models for music: A survey","author":"Ma","year":"2024"},{"key":"ref27","article-title":"MARBLE: Music Audio Representation Benchmark for Universal Evaluation","author":"Yuan","year":"2023"},{"key":"ref28","first-page":"88","article-title":"Codified audio language modeling learns useful representations for music information retrieval","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Castellon"},{"key":"ref29","first-page":"565","article-title":"The Harmonix Set: Beats, Downbeats, and Functional Segment Annotations of Western Popular Music","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Nieto"},{"key":"ref30","first-page":"287","article-title":"RWC Music Database: Popular, Classical and Jazz Music Databases","volume-title":"International Symposium for Music Information Retrieval (ISMIR)","volume":"2","author":"Goto"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248148"},{"key":"ref34","article-title":"Evaluation of cnn-based automatic music tagging models","volume":"abs\/2006.00751","author":"Won","year":"2020","journal-title":"CoRR"},{"key":"ref35","first-page":"396","article-title":"SpecTNT: a time-frequency transformer for music audio","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Lu"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"Tahoe City, CA, USA","start":{"date-parts":[[2025,10,12]]},"end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11231012.pdf?arnumber=11231012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:32:54Z","timestamp":1763191974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11231012\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11231012","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}