{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:40:48Z","timestamp":1784389248718,"version":"3.55.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747252","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"416-420","source":"Crossref","is-referenced-by-count":21,"title":["To Catch A Chorus, Verse, Intro, or Anything Else: Analyzing a Song with Structural Functions"],"prefix":"10.1109","author":[{"given":"Ju-Chiang","family":"Wang","sequence":"first","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun-Ning","family":"Hung","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Center for Music Technology,Atlanta,GA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordan B. L.","family":"Smith","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"769","article-title":"Semi-supervised music tagging transformer","author":"won","year":"2021","journal-title":"ISMIR"},{"key":"ref38","article-title":"The importance of detecting boundaries in music structure annotation","author":"serra","year":"2012","journal-title":"Proc MIR"},{"key":"ref33","article-title":"OMRAS2 metadata project 2009","author":"mauch","year":"2009","journal-title":"ISMIR late-breaking news and demos"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref31","article-title":"Spijkervet\/torchaudio-augmentations","author":"spijkervet","year":"2021"},{"key":"ref30","article-title":"Evaluation of CNN-based automatic music tagging models","author":"won","year":"2020","journal-title":"Sound and Music Computing Conference"},{"key":"ref37","first-page":"730","article-title":"Supervised metric learning for music structure features","author":"wang","year":"2021","journal-title":"ISMIR"},{"key":"ref36","first-page":"547","article-title":"Systematic exploration of computational music structure research","author":"nieto","year":"2016","journal-title":"ISMIR"},{"key":"ref35","article-title":"mir eval: A transparent implementation of common MIR metrics","author":"raffel","year":"2014","journal-title":"ISMIR"},{"key":"ref34","first-page":"303","article-title":"Improving Markov model based music piece structure labelling with acoustic information","author":"paulus","year":"2010","journal-title":"ISMIR"},{"key":"ref10","first-page":"565","article-title":"The Harmonix Set: Beats, downbeats, and functional segment annotations of western popular music","author":"nieto","year":"2019","journal-title":"ISMIR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.869637"},{"key":"ref12","first-page":"417","article-title":"Boundary detection in music structure analysis using convolutional neural networks","author":"ullrich","year":"2014","journal-title":"ISMIR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413773"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2001.969531"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053669"},{"key":"ref16","first-page":"396","article-title":"SpecTNT: A time-frequency transformer for music audio","author":"lu","year":"2021","journal-title":"ISMIR"},{"key":"ref17","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref18","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682278"},{"key":"ref28","first-page":"791","article-title":"MusicBERT: Symbolic music understanding with large-scale pretraining","author":"zeng","year":"2021","journal-title":"Findings of ACL"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683492"},{"key":"ref27","article-title":"Music Transformer: Generating music with long-term structure","author":"huang","year":"2018","journal-title":"ICLRE"},{"key":"ref3","first-page":"531","article-title":"Music boundary detection using neural networks on combined features and two-level annotations","author":"grill","year":"2015","journal-title":"ISMIR"},{"key":"ref6","article-title":"Signal processing methods for drum transcription and music structure analysis","author":"paulus","year":"2009","journal-title":"Ph D thesis"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747048"},{"key":"ref5","first-page":"594","article-title":"Deep embeddings and section fusion improve music segmentation","author":"salamon","year":"2021","journal-title":"ISMIR"},{"key":"ref8","article-title":"Audio-based music structure analysis: Current trends, open challenges, and applications","volume":"3","author":"nieto","year":"2020","journal-title":"Trans ISMIR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02518-1_11"},{"key":"ref2","first-page":"406","article-title":"Hierarchical evaluation of segment boundary detection","author":"mcfee","year":"2015","journal-title":"ISMIR"},{"key":"ref9","first-page":"555","article-title":"Design and creation of a large-scale database of structural annotations","author":"smith","year":"2011","journal-title":"ISMIR"},{"key":"ref1","first-page":"405","article-title":"Analyzing song structure with spectral clustering","author":"mcfee","year":"2014","journal-title":"ISMIR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/964696.964700"},{"key":"ref22","article-title":"Modeling the compatibility of stem tracks to generate music mashups","author":"huang","year":"2021","journal-title":"AAAI Conference"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2347135"},{"key":"ref24","first-page":"75","article-title":"Is music structure annotation multidimensional? A proposal for robust local music annotation","author":"peeters","year":"2009","journal-title":"Int'l Worksh"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.4324\/9781315166100"},{"key":"ref26","article-title":"RWC Music Database: Popular, classical and jazz music databases","volume":"2","author":"goto","year":"2002","journal-title":"ISMIR"},{"key":"ref25","article-title":"Annotator’s guide","year":"0"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747252.pdf?arnumber=9747252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:09:50Z","timestamp":1660579790000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747252\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747252","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}