{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T12:55:22Z","timestamp":1791896122451,"version":"4.3.4"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2010,2,1]],"date-time":"2010-02-01T00:00:00Z","timestamp":1264982400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2010,2]]},"DOI":"10.1109\/tasl.2009.2026503","type":"journal-article","created":{"date-parts":[[2009,7,1]],"date-time":"2009-07-01T14:18:27Z","timestamp":1246457907000},"page":"310-319","source":"Crossref","is-referenced-by-count":140,"title":["On the Improvement of Singing Voice Separation for Monaural Recordings Using the MIR-1K Dataset"],"prefix":"10.1109","volume":"18","author":[{"family":"Chao-Ling Hsu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J.-S.R.","family":"Jang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","article-title":"using voice segment to improve artist classification of music","author":"berenzweig","year":"2002","journal-title":"Proc AES 22nd Int Conf Virtual Synth Entertainment Audio"},{"key":"ref31","article-title":"a svm-based classification approach to musical audio","author":"maddage","year":"2003","journal-title":"Proc Int Conf Music Inform Retrieval"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540176"},{"key":"ref10","first-page":"485","author":"hu","year":"2006","journal-title":"Acoustic Echo and Noise Control"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-22794-6_12"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1121\/1.2939132"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2004.832812"},{"key":"ref14","author":"kim","year":"2003","journal-title":"Singing voice analysis\/synthesis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2006.38"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1109\/ICASSP.2008.4517548","article-title":"three techniques for improving automatic synchronization between music and lyrics: fricative sound detection, filler model, and novel feature vectors for vocal activity detection","author":"fujihara","year":"2008","journal-title":"Proc 2008 IEEE Int Conf Acoust Speech Signal Process (ICASSP'08)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2008.4607710"},{"key":"ref18","first-page":"3365","article-title":"on designing and evaluating speech event detectors","author":"li","year":"2005","journal-title":"Proc Inter Speech"},{"key":"ref19","article-title":"an auditory streaming approach on melody extraction","author":"dressler","year":"2006","journal-title":"Extended Abstract for ISMIR 2006"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref4","first-page":"337","article-title":"separation of vocals from polyphonic audio recordings","author":"vembu","year":"2005","journal-title":"Proc Int Symp Music Inf Retrieval (ISMIR'05)"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"maximum likelihood from incomplete data via the em algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"J R Statist Soc"},{"key":"ref3","first-page":"52","article-title":"disambiguating music emotion using software agents","author":"yang","year":"2004","journal-title":"Proc Symp Music Inf Retrieval (ISMIR'04)"},{"key":"ref6","first-page":"17","article-title":"combining pitch-based inference and non-negative spectrogram factorization in separating vocals from polyphonic music","author":"virtanen","year":"2008","journal-title":"Proc ISCA Tutorial and Research Workshop on Statistical and Perceptual Audition (SAPA'08)"},{"key":"ref29","first-page":"763","article-title":"proposals for performance measurement in source separation","author":"gribonval","year":"2003","journal-title":"Proc Int Symp ICA BSS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.889789"},{"key":"ref8","article-title":"separating a foreground singer from background music","author":"raj","year":"2007","journal-title":"Proc Int Symp Frontiers Res Speech Music (FRSM)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.899291"},{"key":"ref2","first-page":"33","article-title":"system and method for automatic singer identification","author":"zhang","year":"2003","journal-title":"Proc IEEE Int Conf Multimedia and Expo (ICME)"},{"key":"ref9","first-page":"375","author":"brown","year":"2006","journal-title":"Listening to Speech An Auditory Perspective"},{"key":"ref1","first-page":"1197","article-title":"an automatic singing transcription system with multilingual singing lyric recognizer and robust melody tracker","author":"wang","year":"2003","journal-title":"Proc 8th Eur Conf Speech Commun Technol"},{"key":"ref20","first-page":"247","article-title":"sinusoidal extraction using an efficient implementation of a multi-resolution fft","author":"dressler","year":"2006","journal-title":"Proc Int Conf Digital Audio Effects (DAFx-06)"},{"key":"ref22","author":"zavarehei","year":"2005","journal-title":"Sample Speech Enhancement Methods"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543199"},{"key":"ref24","author":"stevens","year":"1998","journal-title":"Acoustic Phonetics"},{"key":"ref23","author":"weintraub","year":"1985","journal-title":"A theory and computational model of auditory monaural sound separation"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1142\/9789812772961_0002"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/5325825\/05153305.pdf?arnumber=5153305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,10]],"date-time":"2025-02-10T15:37:10Z","timestamp":1739201830000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5153305\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,2]]},"references-count":32,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2009.2026503","relation":{},"ISSN":["1558-7916"],"issn-type":[{"value":"1558-7916","type":"print"}],"subject":[],"published":{"date-parts":[[2010,2]]}}}