{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:37:35Z","timestamp":1765546655973,"version":"3.37.3"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["Contract 2017YFB1002201"],"award-info":[{"award-number":["Contract 2017YFB1002201"]}]},{"name":"National Natural Science Fund for Distinguished Young Scholar","award":["61625204"],"award-info":[{"award-number":["61625204"]}]},{"name":"State Key Program of the National Science Foundation of China","award":["61836006"],"award-info":[{"award-number":["61836006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2020.3030484","type":"journal-article","created":{"date-parts":[[2020,10,13]],"date-time":"2020-10-13T19:51:58Z","timestamp":1602618718000},"page":"1-13","source":"Crossref","is-referenced-by-count":3,"title":["Hierarchical Regulated Iterative Network for Joint Task of Music Detection and Music Relative Loudness Estimation"],"prefix":"10.1109","volume":"29","author":[{"given":"Bijue","family":"Jia","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6551-3884","authenticated-orcid":false,"given":"Jiancheng","family":"Lv","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5727-2790","authenticated-orcid":false,"given":"Xi","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Yao","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Shenglan","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-2045"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1042"},{"key":"ref33","first-page":"5649","article-title":"Weakly-supervised temporal localization via occurrence count learning","author":"schroeter","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-019-00607-x"},{"article-title":"Event detection in musical audio","year":"2016","author":"b\u00f6ck","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301817"},{"article-title":"A two-step system for sound event localization and detection","year":"2019","author":"nguyen","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2895254"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2623565"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"ref27","first-page":"1","article-title":"Meta multi-task learning for sequence modeling","author":"chen","year":"0","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016916"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.29"},{"key":"ref1","first-page":"1","article-title":"Automatic music detection in television productions","author":"seyerlehner","year":"0","journal-title":"Proc 10th Int Conf Digital Audio Effects (DAFx-07)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.151"},{"key":"ref24","first-page":"2873","article-title":"Recurrent neural network for text classification with multi-task learning","author":"liu","year":"2016","journal-title":"Proc 25th Int Joint Conf Artif Intell"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2926728"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1486"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/473"},{"key":"ref50","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref51","first-page":"448","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref52","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"0","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"ref10","first-page":"1","article-title":"Music and\/or speech detection MIREX 2018 submission","author":"mel\u00e9ndez-catal\u00e1n","year":"2018","journal-title":"Music Information Retrieval Evaluation eX-change"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357885"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2098869"},{"key":"ref13","first-page":"255","article-title":"Joint beat and downbeat tracking with recurrent neural networks","author":"b\u00f6ck","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref14","first-page":"150","article-title":"Drum transcription via joint beat and drum modeling using convolutional recurrent neural networks","author":"vogl","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"article-title":"Multitask learning for fundamental frequency estimation in music","year":"2018","author":"bittner","key":"ref15"},{"key":"ref16","first-page":"486","article-title":"Multi-task learning of tempo and beat: Learning one to improve the other","author":"b\u00f6ck","year":"0","journal-title":"Proc 20th Int Soc for Music Inf Retrieval Conf"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298652"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596192"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543290"},{"article-title":"Automatic speech\/music discrimination in audio files","year":"2010","author":"ericsson","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758084"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-019-0152-1"},{"key":"ref7","first-page":"1","article-title":"Unsupervised feature learning for speech and music detection in radio broadcasts","author":"schl\u00fcter","year":"0","journal-title":"Proc Int Conf Digital Audio Effects"},{"article-title":"Musan: A music, speech, and noise corpus","year":"2015","author":"snyder","key":"ref49"},{"key":"ref9","first-page":"229","article-title":"Temporal convolutional networks for speech and music detection in radio broadcast","author":"lemaire","year":"0","journal-title":"Proc Int Soc for Music Inf Retrieval Conf"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.11.020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00805"},{"year":"2015","key":"ref48","article-title":"Muspeak speech and music detection dataset"},{"year":"2012","key":"ref47","article-title":"Gtzan speech and music dataset"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2019.2936801"},{"article-title":"B-cnn: Branch convolutional neural network for hierarchical classification","year":"2017","author":"zhu","key":"ref41"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref43","first-page":"5075","article-title":"Hierarchical multi-label classification networks","author":"wehrmann","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09222227.pdf?arnumber=9222227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:55Z","timestamp":1652194435000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9222227\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.3030484","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2021]]}}}