{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T15:40:45Z","timestamp":1777477245883,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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 Signal Process. Mag."],"published-print":{"date-parts":[[2019,1]]},"DOI":"10.1109\/msp.2018.2875133","type":"journal-article","created":{"date-parts":[[2018,12,25]],"date-time":"2018-12-25T19:47:00Z","timestamp":1545767220000},"page":"82-94","source":"Crossref","is-referenced-by-count":31,"title":["An Introduction to Signal Processing for Singing-Voice Analysis: High Notes in the Effort to Automate the Understanding of Vocals in Music"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9211-9564","authenticated-orcid":false,"given":"Eric J.","family":"Humphrey","sequence":"first","affiliation":[]},{"given":"Sravana","family":"Reddy","sequence":"additional","affiliation":[]},{"given":"Prem","family":"Seetharaman","sequence":"additional","affiliation":[]},{"given":"Aparna","family":"Kumar","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7757-2232","authenticated-orcid":false,"given":"Rachel M.","family":"Bittner","sequence":"additional","affiliation":[]},{"given":"Andrew","family":"Demetriou","sequence":"additional","affiliation":[]},{"given":"Sankalp","family":"Gulati","sequence":"additional","affiliation":[]},{"given":"Andreas","family":"Jansson","sequence":"additional","affiliation":[]},{"given":"Tristan","family":"Jehan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7754-7042","authenticated-orcid":false,"given":"Bernhard","family":"Lehner","sequence":"additional","affiliation":[]},{"given":"Anna","family":"Krupse","sequence":"additional","affiliation":[]},{"given":"Luwei","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854174"},{"key":"ref38","first-page":"532","article-title":"Lyrics recognition from a singing voice based on finite state automaton for music information retrieval","author":"hosoya","year":"0","journal-title":"Proc Int Conf Music Information Retrieval (ISMIR)"},{"key":"ref33","first-page":"115","article-title":"Vocarefiner: An interactive singing recording system with integration of multiple singing recordings","author":"nakano","year":"0","journal-title":"Proc Sound Music Comput Conf (SMC)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947660"},{"key":"ref31","first-page":"437","article-title":"Low-delay singing voice alignment to text","author":"loscos","year":"0","journal-title":"Proc Int Computer Music Conf (ICMC)"},{"key":"ref30","first-page":"568","article-title":"Towards automatic identification of singing language in popular music recordings","author":"tsai","year":"0","journal-title":"Proc Int Conf Music Information Retrieval (ISMIR)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2159595"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2159577"},{"key":"ref35","first-page":"23","article-title":"Lyrics-to-audio alignment and its applications","author":"fujihara","year":"2012","journal-title":"Multimodal Music Processing"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911559"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-55004-5_15"},{"key":"ref40","article-title":"Bootstrapping a system for phoneme recognition and keyword spotting in unaccompanied singing","author":"kruspe","year":"0","journal-title":"Late-Breaking Workshop 17th Conf Int Society for Music Information Retrieval (ISMIR)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177945"},{"key":"ref12","article-title":"Deep clustering and conventional networks for music separation: Stronger together","author":"luo","year":"2016"},{"key":"ref13","article-title":"SISEC 2018: State of the art in musical audio source separation-subjective selection of the best algorithm","author":"ward","year":"0","journal-title":"Proc 4th Workshop on Intelligent Music Production"},{"key":"ref14","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 Society for Music Inf Retrieval Conf (ISMIR)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2013.821496"},{"key":"ref16","first-page":"468","article-title":"Vocalset: A singing voice dataset","author":"wilkins","year":"0","journal-title":"Proc Int Society for Music Inf Retrieval Conf (ISMIR)"},{"key":"ref17","first-page":"507","article-title":"Comparison of the singing style of two jingju schools","author":"repetto","year":"0","journal-title":"Proc Int Society for Music Inf Retrieval Conf (ISMIR)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041386"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2013.866145"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952233"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2007.323266"},{"key":"ref27","first-page":"519","article-title":"Singing\/rap classification of isolated vocal tracks","author":"g\u00e4rtner","year":"0","journal-title":"Proc 11th Int Conf Music Information Retrieval (ISMIR)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495212"},{"key":"ref6","first-page":"514","article-title":"Vocals in music matter: The relevance of vocals in the minds of listeners","author":"demetriou","year":"0","journal-title":"Proc Int Society for Music Inf Retrieval Conf (ISMIR)"},{"key":"ref29","article-title":"Learning a large-scale vocal similarity embedding for music","author":"kumar","year":"0","journal-title":"Proc Machine Learning for Music Discovery Workshop Int Conf Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2014.7015431"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2825108"},{"key":"ref7","first-page":"138","article-title":"Content-based retrieval of music and audio","volume":"3229","author":"foote","year":"0","journal-title":"Proc Multimedia Storage and Archiving Systems II Int Society for Optics and Photonics"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/9781118142882"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2825440"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.129.5.770"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2271648"},{"key":"ref22","first-page":"737","article-title":"Singing voice melody transcription using deep neural networks","author":"rigaud","year":"0","journal-title":"Proc Int Society for Music Inf Retrieval Conf (ISMIR)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952145"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462194"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/NCC.2015.7084866"},{"key":"ref41","first-page":"147","article-title":"Solving misheard lyric search queries using a probabilistic model of speech sounds","author":"hirjee","year":"0","journal-title":"Proc 11th Int Conf Music Information Retrieval (ISMIR)"},{"key":"ref23","first-page":"63","article-title":"Deep salience representations for f0 estimation in polyphonic music","author":"bittner","year":"0","journal-title":"Proc Int Society for Music Inf Retrieval Conf (ISMIR)"},{"key":"ref26","author":"gulati","year":"2016","journal-title":"Computational approaches for melodic description in indian art music corpora"},{"key":"ref43","article-title":"Why is voice interesting?","author":"dixon","year":"0","journal-title":"Proc Int Soc Music Information Retrieval Conf"},{"key":"ref25","first-page":"115","article-title":"Unsupervised clustering of extreme vocal effects","author":"nieto","year":"0","journal-title":"Proc 10th Int Conf Adv Quantitative Laryngol"}],"container-title":["IEEE Signal Processing Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/79\/8588402\/08588417.pdf?arnumber=8588417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:49:20Z","timestamp":1657745360000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8588417\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1]]},"references-count":43,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/msp.2018.2875133","relation":{},"ISSN":["1053-5888","1558-0792"],"issn-type":[{"value":"1053-5888","type":"print"},{"value":"1558-0792","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1]]}}}