{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T13:27:34Z","timestamp":1780061254524,"version":"3.54.0"},"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\/icassp43922.2022.9747048","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"401-405","source":"Crossref","is-referenced-by-count":31,"title":["Modeling Beats and Downbeats with a Time-Frequency Transformer"],"prefix":"10.1109","author":[{"given":"Yun-Ning","family":"Hung","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology,Center for Music Technology,Atlanta,GA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ju-Chiang","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance,Mountain View,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuchen","family":"Song","sequence":"additional","affiliation":[{"name":"ByteDance,Mountain View,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Tsung","family":"Lu","sequence":"additional","affiliation":[{"name":"ByteDance,Mountain View,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minz","family":"Won","sequence":"additional","affiliation":[{"name":"ByteDance,Mountain View,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747252"},{"key":"ref38","article-title":"Analysis of common design choices in deep learning systems for downbeat tracking","author":"fuentes","year":"2018","journal-title":"Proc ISMIR"},{"key":"ref33","first-page":"169","article-title":"One in the jungle: Downbeat detection in hardcore, jungle, and drum and bass","author":"hockman","year":"2012","journal-title":"Proc ISMIR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205244"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865704408099"},{"key":"ref30","article-title":"A computational approach to rhythm description-Audio features for the computation of rhythm periodicity functions and their use in tempo induction and music content processing","author":"gouyon","year":"2005","journal-title":"Ph D Dissertation"},{"key":"ref37","article-title":"mir eval: A transparent implementation of common mir metrics","author":"raffel","year":"2014","journal-title":"Proc ISMIR"},{"key":"ref36","article-title":"Swing ratio estimation","author":"marchand","year":"2015","journal-title":"Proc DAFx"},{"key":"ref35","first-page":"565","article-title":"The Harmonix Set: Beats, downbeats, and functional segment annotations of western popular music","author":"nieto","year":"2019","journal-title":"Proc ISMIR"},{"key":"ref34","article-title":"RWC music database: Popular, classical and jazz music databases","volume":"2","author":"goto","year":"2002","journal-title":"Proc ISMIR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1076\/jnmr.30.1.39.7119"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.854090"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1076\/jnmr.30.2.159.7114"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885257"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2973795"},{"key":"ref15","article-title":"Temporal convolutional networks for musical audio beat tracking","author":"davies","year":"2019","journal-title":"Proc EUSIPCO"},{"key":"ref16","article-title":"Multi-task learning of tempo and beat: Learning one to improve the other","author":"b\u00f6ck","year":"2019","journal-title":"Proc ISMIR"},{"key":"ref17","article-title":"Deconstruct, analyse, reconstruct: How to improve tempo, beat, and downbeat estimation","author":"b\u00f6ck","year":"2020","journal-title":"Proc ISMIR"},{"key":"ref18","article-title":"Joint beat and downbeat tracking with recurrent neural networks","author":"b\u00f6ck","year":"2016","journal-title":"Proc ISMIR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682870"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref4","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL"},{"key":"ref27","author":"davies","year":"2021","journal-title":"Tempo Beat and Downbeat Estimation"},{"key":"ref3","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref6","article-title":"Semi-supervised music tagging transformer","author":"won","year":"2021","journal-title":"Proc ISMIR"},{"key":"ref29","article-title":"Evaluation methods for musical audio beat tracking algorithms","author":"davies","year":"2009","journal-title":"Centre for Digital Music Queen Mary University of London"},{"key":"ref5","article-title":"Toward interpretable music tagging with self-attention","author":"won","year":"2019"},{"key":"ref8","article-title":"A bi-directional transformer for musical chord recognition","author":"park","year":"2019","journal-title":"Proc ISMIR"},{"key":"ref7","first-page":"259","article-title":"Harmony Transformer: Incorporating chord segmentation into harmony recognition","author":"chen","year":"2019","journal-title":"Proc ISMIR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2623565"},{"key":"ref9","article-title":"SpecTNT: A time-frequency transformer for music audio","author":"lu","year":"2021","journal-title":"Proc ISMIR"},{"key":"ref1","article-title":"Enhanced beat tracking with context-aware neural networks","author":"b\u00f6ck","year":"2011","journal-title":"Proc DAFx"},{"key":"ref20","article-title":"Rhythmic pattern modeling for beat and downbeat tracking in musical audio","author":"krebs","year":"2013","journal-title":"Proc ISMIR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045236"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540221"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053669"},{"key":"ref23","article-title":"A spectral difference approach to extracting downbeats in musical audio","author":"davies","year":"2006","journal-title":"Proc EUSIPCO"},{"key":"ref26","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc ECCV"},{"key":"ref25","article-title":"A multi-model approach to beat tracking considering heterogeneous music styles","author":"b\u00f6ck","year":"2014","journal-title":"Proc ISMIR"}],"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\/09747048.pdf?arnumber=9747048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:08Z","timestamp":1660594028000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747048","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}