{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T09:44:41Z","timestamp":1775209481157,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,8,9]],"date-time":"2013-08-09T00:00:00Z","timestamp":1376006400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Intell Inf Syst"],"published-print":{"date-parts":[[2014,6]]},"DOI":"10.1007\/s10844-013-0271-6","type":"journal-article","created":{"date-parts":[[2013,8,8]],"date-time":"2013-08-08T06:06:36Z","timestamp":1375941996000},"page":"333-352","source":"Crossref","is-referenced-by-count":8,"title":["Singer identification based on computational auditory scene analysis and missing feature methods"],"prefix":"10.1007","volume":"42","author":[{"given":"Ying","family":"Hu","sequence":"first","affiliation":[]},{"given":"Guizhong","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,8,9]]},"reference":[{"key":"271_CR1","unstructured":"Bartsch, M.A. (2004). Automatic singer identification in polyphonic music. PhD dissertation, The University of Michigan"},{"key":"271_CR2","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1109\/TSA.2003.822637","volume":"12","author":"MA Bartsch","year":"2004","unstructured":"Bartsch, M.A., & Wakefield, G.H. (2004). Singing voice identification using spectral envelope estimation. IEEE Transactions on Speech and Audio Processing, 12, 100\u2013109.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"271_CR3","unstructured":"Boersma, P., & Weenink, D. (2005). Praat. Doing phonetics by computer [computer program]. Retrieved 31 Mar 2005."},{"key":"271_CR4","doi-asserted-by":"crossref","unstructured":"Cai, W., Li, Q., Guan, X. (2011). Automatic singer identification based on auditory features. In 7th int. conf. natural comput. (ICNC) (Vol. 3, pp. 1624\u20131628).","DOI":"10.1109\/ICNC.2011.6022500"},{"key":"271_CR5","unstructured":"Cano, P., Loscos, A., Bonada, J., De Boer, M., Serra, X. (2000). Voice morphing system for impersonating in karaoke applications. In Proc. ICMC (pp. 109\u2013112)."},{"key":"271_CR6","doi-asserted-by":"crossref","unstructured":"Chang, P. (2009). Pitch oriented automatic singer identification in pop music. In Int. conf. semantic comput. (ICSC) (pp.\u00a0161\u2013166).","DOI":"10.1109\/ICSC.2009.28"},{"key":"271_CR7","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1016\/S0167-6393(00)00034-0","volume":"34","author":"M Cooke","year":"2001","unstructured":"Cooke, M., Green, P., Josifovski, L., Vizinho, A. (2001). Robust automatic speech recognition with missing and unreliable acoustic data. Speech Communication, 34, 267\u2013285.","journal-title":"Speech Communication"},{"issue":"3","key":"271_CR8","doi-asserted-by":"crossref","first-page":"638","DOI":"10.1109\/TASL.2010.2041386","volume":"18","author":"H Fujihara","year":"2010","unstructured":"Fujihara, H., Goto, M., Kitahara, T., Okuno, H.G. (2010). A modeling of singing voice robust to accompaniment sounds and its application to singer identification and vocal-timbre-similarity-based music information retrieval. IEEE Transactions on Audio, Speech, and Language Processing, 18(3), 638\u2013648.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"271_CR9","unstructured":"Fujihara, H., Kitahara, T., Goto, M., Komatani, K., Ogata, T., Okuno, H.G. (2005). Singer identification based on accompaniment sound reduction and reliable frame selection. In Proc. int. soc. music inf. retrieval conf. (ISMIR) (pp.\u00a0329\u2013336)."},{"key":"271_CR10","doi-asserted-by":"crossref","unstructured":"Fujihara, H., Kitahara, T., Goto, M., Komatani, K., Ogata, T., Okuno, H.G. (2006). F0 estimation method for singing voice in polyphonic audio signal based on statistical vocal model and Viterbi search. In Proc. IEEE int. conf. acoust., speech signal process. (ICASSP).","DOI":"10.1109\/ICASSP.2006.1661260"},{"key":"271_CR11","doi-asserted-by":"crossref","unstructured":"Hu, Y., & Liu, G. (2011). Dynamic characteristics of musical note for musical instrument classification. In IEEE int. conf. signal process., commun. and comput. (ICSPCC) (pp. 1\u20136).","DOI":"10.1109\/ICSPCC.2011.6061734"},{"issue":"1","key":"271_CR12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10844-012-0213-8","volume":"40","author":"Y Hu","year":"2013","unstructured":"Hu, Y., & Liu, G. (2013). Instrument identification and pitch estimation in multi-timbre polyphonic musical signals based on probabilistic mixture model decomposition. Journal of Intelligent Inf. Systems, 40(1), 1\u201318.","journal-title":"Journal of Intelligent Inf. Systems"},{"issue":"4","key":"271_CR13","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1109\/TASL.2008.2010633","volume":"17","author":"Z Jin","year":"2009","unstructured":"Jin, Z., & Wang, D.L. (2009). A supervised learning approach to monaural segregation of reverberant speech. IEEE Transactions on Audio, Speech, and Language Processing, 17(4), 625\u2013638.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"271_CR14","doi-asserted-by":"crossref","unstructured":"Khine, S.Z.K., Nwe, T.L., Li, H. (2008). Exploring perceptual based timbre feature for singer identification. In Computer music modeling and retrieval (CMMR. 2007). Lecture notes in computer science (Vol. 4969, pp. 159\u2013171).","DOI":"10.1007\/978-3-540-85035-9_10"},{"key":"271_CR15","unstructured":"Kim, Y.E., & Whitman, B. (2002). Singer identification in popular music recordings using voice coding features. In Proc. int. soc. music inf. retrieval conf. (ISMIR)."},{"key":"271_CR16","unstructured":"Lagrange, M., Ozerov, A., Vincent, E. (2012). Robust singer identification in polyphonic music using melody enhancement and uncertainty-based learning. In Proc. int. soc. music inf. retrieval conf. (ISMIR)."},{"key":"271_CR17","unstructured":"Li, Y., & Wang, D.L. (2005). Detecting pitch of singing voice in polyphonic audio. In Proc. IEEE int. conf. acoust., speech signal process. (ICASSP) (Vol. 3, pp.\u00a0iii\/17\u2013iii\/20)."},{"issue":"4","key":"271_CR18","doi-asserted-by":"crossref","first-page":"1475","DOI":"10.1109\/TASL.2006.889789","volume":"15","author":"Y Li","year":"2007","unstructured":"Li, Y., & Wang, D.L. (2007). Separation of singing voice from music accompaniment for monaural recordings. IEEE Transactions on Audio, Speech, and Language Processing, 15(4), 1475\u20131487.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"271_CR19","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.specom.2008.09.001","volume":"51","author":"Y Li","year":"2009","unstructured":"Li, Y., & Wang, D.L. (2009). On the optimality of ideal binary time-frequency masks. Speech Communication, 51, 230\u2013239.","journal-title":"Speech Communication"},{"key":"271_CR20","doi-asserted-by":"crossref","unstructured":"Maddage, N.C., Xu, C., Wang, Y. (2004). Singer identification based on vocal and instrumental models. In Proc. int. conf. pattern recognition (ICPR) (pp.\u00a0375\u2013378).","DOI":"10.1109\/ICPR.2004.1334225"},{"key":"271_CR21","doi-asserted-by":"crossref","unstructured":"Nwe, T.L., & Li, H. (2008). On fusion of timbre-motivated features for singing voice detection and singer identification. In Proc. IEEE int. conf. acoust., speech signal process. (ICASSP) (pp.\u00a02225\u20132228).","DOI":"10.1109\/ICASSP.2008.4518087"},{"key":"271_CR22","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/j.specom.2004.03.007","volume":"43","author":"B Raj","year":"2004","unstructured":"Raj, B., Seltzer, M.L., Stern, R.M. (2004). Reconstruction of missing features for robust speech recognition. Speech communication, 43, 275\u2013296.","journal-title":"Speech communication"},{"key":"271_CR23","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"Reynolds, D.A., Quatieri, T.F., Dunn, R.B. (2000). Speaker verification using adapted Gaussian mixture models. Digital Signal Processing, 10, 19\u201341.","journal-title":"Digital Signal Processing"},{"key":"271_CR24","doi-asserted-by":"crossref","unstructured":"Shen, J., Cui, B., Shepherd, J., Tan, K.L. (2006). Towards efficient automated singer identification in large music databases. In Proc. int. ACM SIGIR conf. res. develop. inf. retrieval (Vol.\u00a027, No.\u00a03, pp.\u00a059\u201366).","DOI":"10.1145\/1148170.1148184"},{"key":"271_CR25","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1145\/1508850.1508856","volume":"27","author":"J Shen","year":"2009","unstructured":"Shen, J., Shepherd, J., Cui, B., Tan, K.L. (2009). A novel framework for efficient automated singer identification in large music databases. ACM Transactions on Information Systems (TOIS), 27, 18.","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"issue":"10","key":"271_CR31","first-page":"831","volume":"60","author":"S Sofianos","year":"2012","unstructured":"Sofianos, S., et al. (2012). H-semantics: a hybrid approach to singing voice separation. Journal of the Audio Engineering Society, 60(10), 831\u2013841.","journal-title":"Journal of the Audio Engineering Society"},{"key":"271_CR26","doi-asserted-by":"crossref","unstructured":"Tsai, W.H., & Lin, H.P. (2010). Popular singer identification based on cepstrum transformation. In Proc. IEEE int. conf. multimedia expo (ICME) (pp. 584\u2013589).","DOI":"10.1109\/ICME.2010.5583066"},{"issue":"5","key":"271_CR27","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1109\/TASL.2010.2087752","volume":"19","author":"WH Tsai","year":"2011","unstructured":"Tsai, W.H., & Lin, H.P. (2011). Background music removal based on cepstrum transformation for popular singer identification. IEEE Transactions on Audio, Speech, and Language Processing, 19(5), 1196\u20131205.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"8","key":"271_CR28","doi-asserted-by":"crossref","first-page":"2291","DOI":"10.1109\/TASL.2012.2201473","volume":"20","author":"WH Tsai","year":"2012","unstructured":"Tsai, W.H., & Lee, H.C. (2012). Singer identification based on spoken data in voice charaterization. IEEE Transactions on Audio, Speech, and Language Processing, 20(8), 2291\u20132300.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"271_CR29","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/0-387-22794-6_12","volume-title":"Speech separation by humans and machines","author":"DL Wang","year":"2005","unstructured":"Wang, D.L. (2005). On ideal binary mask as the computational goal of auditory scene analysis. In P. Divenyi (Ed.), Speech separation by humans and machines (pp. 181\u2013197). Norwell: Kluwer Academic."},{"key":"271_CR33","doi-asserted-by":"crossref","DOI":"10.1109\/9780470043387","volume-title":"Computational auditory scene analysis: Principles, algorithms and applications","author":"DL Wang","year":"2006","unstructured":"Wang, D.L., & Brown, G.J. (2006). Computational auditory scene analysis: Principles, algorithms and applications. Hoboken: Wiley-IEEE Press."},{"issue":"5","key":"271_CR30","doi-asserted-by":"crossref","first-page":"1608","DOI":"10.1109\/TASL.2012.2186803","volume":"20","author":"X Zhao","year":"2012","unstructured":"Zhao, X., Shao, Y., Wang, D. (2012). CASA-based robust speaker identification. IEEE Transactions on Audio, Speech, and Language Processing, 20(5), 1608\u20131616.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"9","key":"271_CR32","first-page":"710","volume":"56","author":"P Zwan","year":"2008","unstructured":"Zwan, P., & Kostek, B. (2008). System for automatic singing voice recognition. Journal of the Audio Engineering Society, Vibrato and Intonation Parameters, 56(9), 710\u2013723.","journal-title":"Journal of the Audio Engineering Society, Vibrato and Intonation Parameters"}],"container-title":["Journal of Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-013-0271-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10844-013-0271-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-013-0271-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,20]],"date-time":"2019-07-20T15:32:19Z","timestamp":1563636739000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10844-013-0271-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,8,9]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,6]]}},"alternative-id":["271"],"URL":"https:\/\/doi.org\/10.1007\/s10844-013-0271-6","relation":{},"ISSN":["0925-9902","1573-7675"],"issn-type":[{"value":"0925-9902","type":"print"},{"value":"1573-7675","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,8,9]]}}}