{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T07:19:23Z","timestamp":1777619963876,"version":"3.51.4"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2018,8,1]],"date-time":"2018-08-01T00:00:00Z","timestamp":1533081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100002428","name":"Austrian Science Fund (FWF)","doi-asserted-by":"crossref","award":["TRP307-N23"],"award-info":[{"award-number":["TRP307-N23"]}],"id":[{"id":"10.13039\/501100002428","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002428","name":"Austrian Science Fund (FWF)","doi-asserted-by":"crossref","award":["Z159"],"award-info":[{"award-number":["Z159"]}],"id":[{"id":"10.13039\/501100002428","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001821","name":"Vienna Science and Technology Fund","doi-asserted-by":"crossref","award":["NXT17-004"],"award-info":[{"award-number":["NXT17-004"]}],"id":[{"id":"10.13039\/501100001821","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001821","name":"Vienna Science and Technology Fund","doi-asserted-by":"crossref","award":["MA14-018"],"award-info":[{"award-number":["MA14-018"]}],"id":[{"id":"10.13039\/501100001821","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/taslp.2018.2825108","type":"journal-article","created":{"date-parts":[[2018,4,9]],"date-time":"2018-04-09T18:05:33Z","timestamp":1523297133000},"page":"1369-1380","source":"Crossref","is-referenced-by-count":25,"title":["Online, Loudness-Invariant Vocal Detection in Mixed Music Signals"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7754-7042","authenticated-orcid":false,"given":"Bernhard","family":"Lehner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Schluter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerhard","family":"Widmer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","article-title":"RNNLIB: A recurrent neural network library for sequence learning\n problems","author":"graves","year":"2013"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/COMJ_a_00004"},{"key":"ref32","article-title":"Jamendo,\n open your ears","author":"g\u00e9rard","year":"2005"},{"key":"ref31","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1974.1162572"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946764"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_45"},{"key":"ref35","first-page":"287","article-title":"RWC music database: Popular, classical, and\n jazz music databases","volume":"2","author":"goto","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref34","first-page":"393","article-title":"Towards quantifying the ‘album effect’ in artist identification","author":"kim","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.07.001"},{"key":"ref11","first-page":"3","article-title":"Hidden Markov support vector machines","volume":"20","author":"altun","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5108-8"},{"key":"ref13","first-page":"37","article-title":"Automatic assessment of singer traits in popular music: Gender, age, height and race","author":"weninger","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2182510"},{"key":"ref16","first-page":"53","article-title":"Towards light-weight, real-time-capable singing voice detection","author":"lehner","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362337"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855054"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177944"},{"key":"ref28","first-page":"1","article-title":"A simple and effective spectral\n feature for speech detection in mixed audio signals","author":"sonnleitner","year":"0","journal-title":"Proc Int Conf Digit Audio Effects"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2001.969557"},{"key":"ref27","first-page":"309","article-title":"Monaural blind source separation in the context of vocal detection","author":"lehner","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref3","first-page":"233","article-title":"Timbre and melody features for the\n recognition of vocal activity and instrumental solos in polyphonic music","author":"mauch","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref29","author":"sethares","year":"2007","journal-title":"Rhythm and Transforms"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.889789"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959926"},{"key":"ref9","first-page":"8","article-title":"Automatic classification of large musical instrument databases\n using hierarchical classifiers with inertia ratio maximization","author":"peeters","year":"0","journal-title":"Proc 115th Audio Eng Soc Conv"},{"key":"ref1","article-title":"Greatest vocal range, male","year":"2016"},{"key":"ref20","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 Conf Music Inf Retrieval"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","article-title":"Deep learning for event detection, sequence labelling and\n similarity estimation in music signals","author":"schl\u00fcter","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref23","first-page":"545","article-title":"Offline handwriting recognition with multidimensional recurrent neural networks","author":"graves","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref26","first-page":"618","article-title":"Cross-version singing voice detection in classical\n opera recordings","author":"dittmar","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref25","first-page":"209","article-title":"The\n quefrency analysis of time series for echoes: Cepstrum, pseudo-autocovariance, cross-cepstrum, and saphe cracking","author":"bogert","year":"1963","journal-title":"Proceedings of the Symposium on Time Series Analysis"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8356719\/08334252.pdf?arnumber=8334252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:18:06Z","timestamp":1642004286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8334252\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":38,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2825108","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8]]}}}