{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T13:35:32Z","timestamp":1760708132217},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2009,11,10]],"date-time":"2009-11-10T00:00:00Z","timestamp":1257811200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2010,11]]},"DOI":"10.1007\/s11042-009-0416-3","type":"journal-article","created":{"date-parts":[[2009,11,9]],"date-time":"2009-11-09T17:38:18Z","timestamp":1257788298000},"page":"415-435","source":"Crossref","is-referenced-by-count":16,"title":["Improvement to speech-music discrimination using sinusoidal model based features"],"prefix":"10.1007","volume":"50","author":[{"given":"Jalil","family":"Shirazi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shahrokh","family":"Ghaemmaghami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2009,11,10]]},"reference":[{"key":"416_CR1","unstructured":"Abu-E1-Quran AR, Goubran RA, Chan ADC (2006) Adaptive feature selection for speech\/music classifications. In: IEEE International workshop on multimedia signal processing 212\u2013216"},{"key":"416_CR2","doi-asserted-by":"crossref","unstructured":"Ajmera J, McCowan L, Bourlard H (2003) Speech\/music segmentation using entropy and dynamism features in a HMM classification framework. In: ELSEVIER Transactions on Speech communication 351\u2013363","DOI":"10.1016\/S0167-6393(02)00087-0"},{"key":"416_CR3","doi-asserted-by":"crossref","unstructured":"Babu J, Pathari V (2007) Multimedia content segmentation based on speaker recognition.In: IEEE ICSCN 2007, 16\u201319","DOI":"10.1109\/ICSCN.2007.350672"},{"key":"416_CR4","unstructured":"Lin C-C, Chen S-H, Truong T-K, Chang Y (2005) Audio Classification and categorization based on wavelets and support vector machine. In: IEEE Transactions on Speech and Audio Processing 13: 644\u2013651"},{"key":"416_CR5","unstructured":"Cortes C, Vapnik V (1995) Support vector networks. In: Mach. Learn 20: 273\u2013297"},{"key":"416_CR6","unstructured":"Cortizo E, Zurer M, Ferreras F (2005) Application of fisher linear discriminant analysis to speech\/music classification. In: EUROCON 1666\u201316669"},{"key":"416_CR7","unstructured":"Duda R, Hart P, Stock D (2000) Pattern Classification. Wiley"},{"key":"416_CR8","unstructured":"Ei-Maleh K, Klein M, Petrucci G, Kabal P (2000) Speech\/music discrimination for multimedia applications. In: ICASSP 2000 2445\u20132448"},{"key":"416_CR9","unstructured":"Guo G, Li SZ (2003) Content-based audio classification and retrieval by support vector machines. In: IEEE Transactions on Neural Networks 14: 209\u2013215"},{"key":"416_CR10","unstructured":"Hsu C-W, Chang C-C, Lin C-J (2009)A practical guide to support vector classification. In Department of Computer Science, National Taiwan University, http:\/\/www.csie.ntu.edu.tw\/~cjlin\/papers\/guide\/guide.pdf"},{"key":"416_CR11","doi-asserted-by":"crossref","unstructured":"Jensen J, Hansen J.H.L (2001) Speech enhancement using a constrained iterative sinusoidal model. In: IEEE Transactions on Speech and Audio Processing 9: 731\u2013740","DOI":"10.1109\/89.952491"},{"key":"416_CR12","unstructured":"Lagrange M, Marchand S (2007) Estimating the instantaneous frequency of sinusoidal components using phase-based methods. In: Journal of the Audio Engineering Society 55: 385\u2013399"},{"key":"416_CR13","unstructured":"Li SZ (2000) Content-based audio classification and retrieval using the nearest feature line method. In: IEEE Transactions on Speech and Audio Processing 8: 619\u2013625"},{"key":"416_CR14","doi-asserted-by":"crossref","unstructured":"Li D, Sethi I.K, Dimitrova N, McGee T (2001) Classification of general audio for content- based retrieval. In: ELSEVIER Pattern Recognition Letters 533\u2013554","DOI":"10.1016\/S0167-8655(00)00119-7"},{"key":"416_CR15","doi-asserted-by":"crossref","unstructured":"Lu L, Zhang H-J (2002) Content analysis for audio classification and segmentation. In: IEEE Transactions on Speech and Audio Processing 10: 504\u2013516","DOI":"10.1109\/TSA.2002.804546"},{"key":"416_CR16","doi-asserted-by":"crossref","unstructured":"Lu L, Zhang H-J, Li SZ (2003) Content-based audio classification and segmentation by using support vector Machines.: In: Multimedia Systems Journal 482\u2013492","DOI":"10.1007\/s00530-002-0065-0"},{"key":"416_CR17","unstructured":"McAulay RJ, Quatieri TF (1986) Speech analysis\/synthesis based on a sinusoidal representation. In: IEEE Transactions on Acoustic, Speech and Signal Processing ASSP- 34 744\u2013754"},{"key":"416_CR18","doi-asserted-by":"crossref","unstructured":"Moon TK (1996) The Expectation-maximization algorithm. In: IEEE Signal Processing Magazine 13: 47\u201360","DOI":"10.1109\/79.543975"},{"key":"416_CR19","unstructured":"Mowlaee Begzadeh Mahale P, Sayadiyan A, Faez K (2008) Mixed type audio classification using sinusoidal parameters. In Proc. 3rd ICTTA\u201908 1\u20135"},{"key":"416_CR20","unstructured":"Nunes LO, Esquef PAA, Biscainho LWP, Merched R (2008) Partial tracking in sinusoidal modeling- an adaptive prediction-based RLS lattice solution. In: SIGMAP 2008 84\u201391"},{"key":"416_CR21","volume-title":"Digital processing of speech signals","author":"LR Rabiner","year":"1975","unstructured":"Rabiner LR, Shafer RW (1975) Digital processing of speech signals. Prentice-Hall, Englewood Cliffs"},{"key":"416_CR22","doi-asserted-by":"crossref","unstructured":"Ramamohan S, Dandapat S (2006) Sinusoidal model-based analysis and classification of stressed speech. In: IEEE Transactions on Audio, Speech and Language Processing 14: 737\u2013746","DOI":"10.1109\/TSA.2005.858071"},{"key":"416_CR23","doi-asserted-by":"crossref","unstructured":"Regnier L, Peeters G (2009) Singing voice detection in music tracks using direct voice vibrato detection. In: Proceeding of ICASSP 2009 1685\u20131688","DOI":"10.1109\/ICASSP.2009.4959926"},{"key":"416_CR24","doi-asserted-by":"crossref","unstructured":"Sadjadi OS, Ahadi SM, Hazrati O (2007) Unsupervised speech\/music classification using one-class support vector machines. In: 6th IEEE ICICS 1\u20135","DOI":"10.1109\/ICICS.2007.4449839"},{"key":"416_CR25","doi-asserted-by":"crossref","unstructured":"Saunders J (1996) Real-time discrimination of broadcast speech\/music. In: Proceeding of ICASSP 1996 993\u2013996","DOI":"10.1109\/ICASSP.1996.543290"},{"key":"416_CR26","unstructured":"Scheirer E, Slaney M (1997) Construction and evaluation of a robust multi-feature speech\/music discriminator. In: Proceeding of ICASSP 1997 21\u201324"},{"key":"416_CR27","unstructured":"Smith JO, Serra X (1987) PARSHL: An analysis\/synthesis program for non-harmonic sound based on sinusoidal representation. http:\/\/www-ccrma.stanford.edu\/~jos\/parshl\/parshl.pdf"},{"key":"416_CR28","doi-asserted-by":"crossref","unstructured":"Somervuo P, Harma A, Fagerlund S (2006) Parametric representation of bird sounds for automatic species recognition. In: IEEE Transactions on Audio, Speech and Language Processing 14: 2252\u20132263","DOI":"10.1109\/TASL.2006.872624"},{"key":"416_CR29","doi-asserted-by":"crossref","unstructured":"Tancerel L, Ragot S, Ruoppilaand VT, Lefebyre R (2000) Combined speech and audio coding by discrimination. In: IEEE work-shop on speech coding, 17\u201320","DOI":"10.1109\/SCFT.2000.878435"},{"key":"416_CR30","unstructured":"Thoshkahana B, Sudha V, Ramakrishnan KR (2006) A speech-music discriminator using HILN model based features. In: ICASSP 2006 425\u2013428"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-009-0416-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-009-0416-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-009-0416-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T03:27:53Z","timestamp":1559359673000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-009-0416-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,11,10]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2010,11]]}},"alternative-id":["416"],"URL":"https:\/\/doi.org\/10.1007\/s11042-009-0416-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,11,10]]}}}