{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:20:20Z","timestamp":1781713220340,"version":"3.54.5"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,2]]},"DOI":"10.1109\/taslp.2018.2877892","type":"journal-article","created":{"date-parts":[[2018,10,24]],"date-time":"2018-10-24T19:17:39Z","timestamp":1540408659000},"page":"268-282","source":"Crossref","is-referenced-by-count":46,"title":["CountNet: Estimating the Number of Concurrent Speakers Using Supervised Learning"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2534-1165","authenticated-orcid":false,"given":"Fabian-Robert","family":"Stoter","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0846-207X","authenticated-orcid":false,"given":"Soumitro","family":"Chakrabarty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernd","family":"Edler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2613-8046","authenticated-orcid":false,"given":"Emanuel A. P.","family":"Habets","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","article-title":"DARPA TIMIT acoustic phonetic continuous speech corpus CDROM","author":"garofolo","year":"1993"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref70","article-title":"The ETAPE corpus for the evaluation of speech-based TV content processing in the french\n language","author":"gravier","year":"0","journal-title":"Proc Int Conf Lang Resources Eval"},{"key":"ref76","article-title":"Webrtc vad v2.0.10","year":"2017"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178348"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078608"},{"key":"ref74","article-title":"THCHS-30: A\n free chinese speech corpus","author":"wang","year":"2015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2017.8309164"},{"key":"ref75","first-page":"85","article-title":"DCASE 2017 challenge setup: Tasks, datasets\n and baseline system","author":"mesaros","year":"2017","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref78","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc ICLR"},{"key":"ref79","article-title":"Keras v1.2.2","author":"chollet","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202328"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282303"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178011"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2015.03.006"},{"key":"ref37","first-page":"436","article-title":"Classification vs.\n regression in supervised learning for single channel speaker count estimation","author":"stter","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref36","first-page":"3399","article-title":"Counting competing speakers in a time\n frame - human versus computer","author":"andrei","year":"0","journal-title":"Proc Interspeech Conf"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493435"},{"key":"ref34","first-page":"101","article-title":"Proposal of a new confidence parameter estimating the number of speakers-an experimental\n investigation","volume":"1","author":"sayoud","year":"2010","journal-title":"J Inf Hiding Multimedia Signal Process"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1142\/S0218488598000094"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177944"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SAM.2012.6250555"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2030854"},{"key":"ref64","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition\n in English and Mandarin","author":"amodei","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952585"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854924"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1109\/TASLP.2017.2690575","article-title":"Convolutional recurrent neural networks for polyphonic sound event\n detection","volume":"25","author":"akr","year":"2017","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2016.7500246"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854950"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref69","first-page":"2546","article-title":"Algorithms for hyper-parameter\n optimization","author":"bergstra","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","author":"pierre","year":"2010","journal-title":"Handbook of Blind Source Separation"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799609"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1038\/003281a0","article-title":"The power of numerical discrimination","volume":"3","author":"jevons","year":"1871","journal-title":"Nature"},{"key":"ref21","first-page":"389","article-title":"An experiment about estimating the number of instruments\n in polyphonic music: a comparison between internet and laboratory results","author":"schoeffler","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3758\/BF03204162"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.471"},{"key":"ref26","first-page":"742","article-title":"Stereo source separation and source\n counting with map estimation with dirichlet prior considering spatial aliasing problem","author":"araki","year":"0","journal-title":"Proc Int Conf Latent Variable Anal Signal Separat"},{"key":"ref25","article-title":"Source number estimation and clustering for underdetermined blind source separation","author":"loesch","year":"0","journal-title":"Proc Int Workshop Acoust Echo Noise Control"},{"key":"ref50","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-4286-2","author":"berger","year":"1985","journal-title":"Statistical Decision Theory and Bayesian Analysis"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-009-0277-8"},{"key":"ref59","first-page":"44","article-title":"Learning to pinpoint singing voice from weakly labeled examples","author":"schl\u00fcter","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref58","first-page":"121","article-title":"Exploring data augmentation for improved singing voice detection with neural networks","author":"schl\u00fcter","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081710"},{"key":"ref56","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc ICLR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9939-1994-1195477-8"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459191"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.561"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2678684"},{"key":"ref11","article-title":"Enhancing lstm rnn-based speech overlap\n detection by artificially mixed data","author":"hagerer","year":"0","journal-title":"Proc Audio Eng Soc Int Conf Semantic Audio"},{"key":"ref40","first-page":"191","article-title":"Convolutional neural network in the task of speaker change detection","author":"hr\u00faz","year":"0","journal-title":"Proc Int Conf Speech Comput"},{"key":"ref12","first-page":"1198","article-title":"Detecting overlapped speech on short timeframes using deep learning","author":"andrei","year":"0","journal-title":"Proc Interspeech Conf"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946318"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1121\/1.408434"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-015-0910-9"},{"key":"ref81","author":"mcculloch","year":"2006","journal-title":"Generalized Linear Mixed Models"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.415287"},{"key":"ref84","article-title":"Striving for simplicity: The all\n convolutional net","author":"springenberg","year":"2015","journal-title":"ICLR (workshop track)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2307\/40285438"},{"key":"ref83","article-title":"Room impulse response (RIR) generator","author":"habets","year":"2016"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362751"},{"key":"ref3","first-page":"1","article-title":"An open-source state-of-the-art toolbox for broadcast news diarization","author":"rouvier","year":"0","journal-title":"Proc Interspeech Conf"},{"key":"ref6","first-page":"3827","article-title":"Speaker change detection\n in broadcast TV using bidirectional long short-term memory networks","author":"yin","year":"0","journal-title":"Proc Interspeech Conf"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2016.12.009"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-326","article-title":"Speech overlap detection in a two-pass speaker diarization system","author":"huijbregts","year":"2009","journal-title":"Proc Interspeech Conf"},{"key":"ref85","article-title":"Deep\n inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2013","journal-title":"ICLR (workshop track)"},{"key":"ref7","first-page":"32","article-title":"Two's a crowd: Improving speaker diarization by automatically identifying and excluding overlapped speech","author":"boakye","year":"0","journal-title":"Proc Interspeech Conf"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472678"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299031"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.jml.2007.11.007"},{"key":"ref9","first-page":"1668","article-title":"Detecting overlapping\n speech with long short-term memory recurrent neural networks","author":"geiger","year":"0","journal-title":"Proc Interspeech Conf"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1177\/002383096400700208"},{"key":"ref46","first-page":"483","article-title":"Counting\n in the wild","author":"arteta","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298684"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967300"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5220\/0006097300270033"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806337"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301276"},{"key":"ref43","first-page":"339","article-title":"Deep\n convolutional neural networks for human embryonic cell counting","author":"khan","year":"0","journal-title":"Proc Eur Conf Comput Vis"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8552740\/08506601.pdf?arnumber=8506601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:45:01Z","timestamp":1657745101000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8506601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2]]},"references-count":88,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2877892","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2]]}}}