{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:10:23Z","timestamp":1778947823168,"version":"3.51.4"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3268572","type":"journal-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T21:14:55Z","timestamp":1682025295000},"page":"1681-1692","source":"Crossref","is-referenced-by-count":20,"title":["Speaker Counting and Separation From Single-Channel Noisy Mixtures"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2186-5420","authenticated-orcid":false,"given":"Srikanth Raj","family":"Chetupalli","sequence":"first","affiliation":[{"name":"International Audio Laboratories, A Joint Institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer IIS, Erlangen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2613-8046","authenticated-orcid":false,"given":"Emanu\u00ebl A. P.","family":"Habets","sequence":"additional","affiliation":[{"name":"International Audio Laboratories, A Joint Institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer IIS, Erlangen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10849"},{"key":"ref12","first-page":"7164","article-title":"Voice separation with an unknown number of multiple speakers","author":"nachmani","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref31","first-page":"367","article-title":"MIR_EVAL: A transparent implementation of common MIR metrics","author":"raffel","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414205"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1550"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2018.07.001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2468583"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168152"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053327"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413627"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688217"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747373"},{"key":"ref26","article-title":"CSR-I (WSJ0) complete LDC93S6A","author":"garofolo","year":"1993"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref20","article-title":"Layer normalization","author":"ba","year":"0","journal-title":"Proc Adv NIPS Deep Learn Symp"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref21","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref28","first-page":"1","article-title":"Adam: A method for stochastic gradient descent","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref27","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"ravanelli","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413670"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462646"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10105940.pdf?arnumber=10105940","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T18:05:37Z","timestamp":1684778737000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10105940\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3268572","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}