{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T15:20:28Z","timestamp":1790695228342,"version":"4.1.0"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"publisher","award":["637422"],"award-info":[{"award-number":["637422"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.3029652","type":"journal-article","created":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T15:49:18Z","timestamp":1602172158000},"page":"2895-2905","source":"Crossref","is-referenced-by-count":35,"title":["Active Learning for Sound Event Detection"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6151-6460","authenticated-orcid":false,"given":"Zhao","family":"Shuyang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8855-0415","authenticated-orcid":false,"given":"Toni","family":"Heittola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4604-9729","authenticated-orcid":false,"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref32","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"tarvainen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.848882"},{"key":"ref11","first-page":"3904","article-title":"Active learning for automatic speech recognition","author":"hakkani-t\u00fcr","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0162075"},{"key":"ref13","first-page":"751","article-title":"Active learning for sound event classification by clustering unlabeled data","author":"zhao","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref14","first-page":"116","article-title":"An active learning method using clustering and committee-based sample selection for sound event classification","author":"zhao","year":"0","journal-title":"Proc 16th Int Workshop Acoust Signal Enhancement"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462200"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362478"},{"key":"ref27","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"0","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0214168"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2930913"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857575"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1135777.1135870"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2858559"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5626\/JCSE.2012.6.1.40"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1021\/ci049810a"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2017.08.006"},{"key":"ref20","first-page":"85","article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"0","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.925152"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073168"},{"key":"ref26","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref25","first-page":"4841","article-title":"Bic-based audio segmentation by divide-and-conquer","author":"cheng","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09217930.pdf?arnumber=9217930","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:31:43Z","timestamp":1651066303000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9217930\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.3029652","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}