{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T11:17:48Z","timestamp":1782386268466,"version":"3.54.5"},"reference-count":35,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462159","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"436-440","source":"Crossref","is-referenced-by-count":21,"title":["Classification vs. Regression in Supervised Learning for Single Channel Speaker Count Estimation"],"prefix":"10.1109","author":[{"given":"Fabian-Robert","family":"Stoter","sequence":"first","affiliation":[{"name":"International Audio Laboratories, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Fraunhofer institute for Integrated Circuits (IIS), Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soumitro","family":"Chakrabarty","sequence":"additional","affiliation":[{"name":"International Audio Laboratories, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Fraunhofer institute for Integrated Circuits (IIS), Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernd","family":"Edler","sequence":"additional","affiliation":[{"name":"International Audio Laboratories, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Fraunhofer institute for Integrated Circuits (IIS), Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emanuel A. P.","family":"Habets","sequence":"additional","affiliation":[{"name":"International Audio Laboratories, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Fraunhofer institute for Integrated Circuits (IIS), Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","first-page":"44","article-title":"Learning to pinpoint singing voice from weakly labeled examples","author":"schl\u00fcter","year":"2016","journal-title":"Proc of ISMIR)"},{"key":"ref32","first-page":"2135","article-title":"Deep neural network based instrument extraction from music","author":"uhlich","year":"2015","journal-title":"Proc IEEE (ICASSP)"},{"key":"ref31","article-title":"TUT database for acoustic scene classification and sound event detection","author":"mesaros","year":"2016","journal-title":"Proc European Signal Processing Conf (EUSIPCO)"},{"key":"ref30","year":"0","journal-title":"WebRTC VAD v2 0 10"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-015-0910-9"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806337"},{"key":"ref11","article-title":"Counting everyday objects in everyday scenes","author":"chattopadhyay","year":"2017","journal-title":"Proc Intl IEEE Conf on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref12","first-page":"339","article-title":"Deep convolutional neural networks for human embryonic cell counting","author":"khan","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref13","first-page":"90","article-title":"Learning to count with deep object features","author":"segu\u00ed","year":"2015","journal-title":"Proc Intl IEEE Conf on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref14","first-page":"833","article-title":"Cross-scene crowd counting via deep convolutional neural networks","author":"zhang","year":"2015","journal-title":"Proc Intl IEEE Conf on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref15","first-page":"483","article-title":"Counting in the wild","author":"arteta","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref16","author":"marsden","year":"2016","journal-title":"Fully convolutional crowd counting on highly congested scenes"},{"key":"ref17","first-page":"640","article-title":"Crowd-net: A deep convolutional network for dense crowd counting","author":"boominathan","year":"2016","journal-title":"Proc ACM Intern Conf Multimedia (ACMMM)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299031"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-009-0277-8"},{"key":"ref28","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref4","first-page":"ii-197","article-title":"Estimating number of speakers by the modulation characteristics of speech","volume":"2","author":"arai","year":"2003","journal-title":"Proc IEEE (ICASSP)"},{"key":"ref27","first-page":"6645","article-title":"Speech recognition with deep recurrent neural networks","author":"graves","year":"2013","journal-title":"Proc IEEE (ICASSP)"},{"key":"ref3","first-page":"459","article-title":"Source counting in speech mixtures by nonparametric bayesian estimation of an infinite Gaussian mixture model","author":"walter","year":"2015","journal-title":"Proc IEEE (ICASSP)"},{"key":"ref6","first-page":"43","article-title":"Crowd++: Unsupervised speaker count with smartphones","volume":"13","author":"xu","year":"2013","journal-title":"Proceedings of the 2013 ACM UbiComb"},{"key":"ref29","first-page":"5206","article-title":"Librispeech: an asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proc IEEE (ICASSP)"},{"key":"ref5","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":"Journal of Information Hiding and Multimedia Signal Processing"},{"key":"ref8","article-title":"Permutation invariant training of deep models for speaker-independent multitalker speech separation","author":"yu","year":"2017","journal-title":"Proc IEEE (ICASSP)"},{"key":"ref7","article-title":"Counting competing speakers in a time frame - human versus computer","author":"andrei","year":"2015","journal-title":"Proc Interspeech Conf"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2015.03.006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref20","article-title":"DeepSetNet: Predicting sets with deep neural networks","author":"rezatofighi","year":"2017","journal-title":"Proc IEEE Intl Conference on Computer Vision (ICCV)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9939-1994-1195477-8"},{"key":"ref21","first-page":"545","article-title":"Bayesian poisson regression for crowd counting","author":"chan","year":"2009","journal-title":"Proc IEEE Intl Conference on Computer Vision (ICCV)"},{"key":"ref24","article-title":"Enhancing LSTM RNN-Based speech overlap detection by artificially mixed data","author":"hagerer","year":"2017","journal-title":"Proceedings of the Audio Engineering Society (AES) Conference on Semantic Audio"},{"key":"ref23","first-page":"121","article-title":"Singing voice detection with deep recurrent neural networks","author":"leglaive","year":"2015","journal-title":"Proc IEEE (ICASSP)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1142\/S0218488598000094"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB, Canada","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462159.pdf?arnumber=8462159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T05:07:31Z","timestamp":1623215251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462159","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}