{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T02:33:48Z","timestamp":1790303628075,"version":"4.1.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ministry of Innovation and Research of Romania"},{"DOI":"10.13039\/501100006595","name":"UEFISCDI","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006595","id-type":"DOI","asserted-by":"crossref"}]},{"name":"SPIA-VA","award":["2SOL\/2017"],"award-info":[{"award-number":["2SOL\/2017"]}]},{"name":"SPIA-VA","award":["PN-III-P2-2.1-SOL-2016-02-0002"],"award-info":[{"award-number":["PN-III-P2-2.1-SOL-2016-02-0002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1109\/jstsp.2019.2910759","type":"journal-article","created":{"date-parts":[[2019,7,24]],"date-time":"2019-07-24T19:51:02Z","timestamp":1563997862000},"page":"850-862","source":"Crossref","is-referenced-by-count":22,"title":["Overlapped Speech Detection and Competing Speaker Counting\u2013\u2010Humans Versus Deep Learning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7975-6879","authenticated-orcid":false,"given":"Valentin","family":"Andrei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8711-3854","authenticated-orcid":false,"given":"Horia","family":"Cucu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1710-8010","authenticated-orcid":false,"given":"Corneliu","family":"Burileanu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"173","article-title":"Deep speech 2: End-to-End speech recognition in english and mandarin","author":"amodei","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/89.928915"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref30","article-title":"Matlab toolbox for speech processing","author":"brookes","year":"2002"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2009.02.001"},{"key":"ref36","first-page":"1417","article-title":"One microphone blind dereverberation based on quasiperiodicity of speech signals","author":"nakatani","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2003.09.005"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref27","first-page":"3","article-title":"Announcing the AMI meeting corpus","volume":"11","author":"carletta","year":"2006","journal-title":"ELRA Newsletter"},{"key":"ref29","article-title":"Room impulse response (RIR) generator","author":"habets","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202328"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462159"},{"key":"ref21","first-page":"101","article-title":"Proposal of a new confidence parameter estimating the number of speakers-an experimental investigation","volume":"1","author":"sayoud","year":"2010","journal-title":"J Inf Hiding Multimedia Signal Process"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493435"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2426656.2426673"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISWPC.2010.5483789"},{"key":"ref50","article-title":"What is the","author":"martin","year":"0"},{"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 Int Conf Mach Learn"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2877892"},{"key":"ref56","article-title":"Convolutional sequence modeling revisited","author":"bai","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1878"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2324564"},{"key":"ref53","first-page":"1388","article-title":"Let me finish: Automatic conflict detection using speaker overlap","author":"grezes","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","volume":"abs 1412 6980","author":"kingma","year":"0","journal-title":"CoRR"},{"key":"ref10","first-page":"1891","article-title":"Speaker Identification in Overlapped speech","author":"tsai","year":"2010","journal-title":"J Inf Sci Eng"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288840"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638174"},{"key":"ref13","article-title":"TIMIT acoustic-phonetic continuous speech corpus LDC93S1","year":"1993"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2346315"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178867"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178986"},{"key":"ref17","first-page":"690","article-title":"Using linguistic information to detect overlapped speech","author":"geiger","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref18","first-page":"1668","article-title":"Detecting overlapped speech with long short-term memory recurrent neural networks","author":"geiger","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-188"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinph.2011.07.030"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/0898929053467631"},{"key":"ref6","first-page":"467","article-title":"Detecting the number of competing speakers–human selective hearing versus spectrogram distance-based estimator","author":"andrei","year":"0","journal-title":"Proc INTERSPEECH 14th Annu Conf Int Speech Commun Assoc"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.415287"},{"key":"ref8","first-page":"3999","article-title":"Counting competing speakers in a timeframe–human versus computer","author":"andrei","year":"0","journal-title":"Proc INTERSPEECH 14th Annu Conf Int Speech Commun Assoc"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-015-0910-9"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518619"},{"key":"ref46","article-title":"Convolutional networks for images, speech, and time-series","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178847"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref47","first-page":"11","article-title":"Progress in digital integrated electronics","volume":"11","author":"moore","year":"0","journal-title":"Proc IEEE Prog Digit Integrated Electron Int Electron Devices Meeting"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref44","article-title":"Learning the speech front-end with raw waveform CLDNNs","author":"sainath","year":"0","journal-title":"InterSpeech"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/8771267\/08688468.pdf?arnumber=8688468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:08:16Z","timestamp":1657746496000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8688468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":57,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2019.2910759","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8]]}}}