{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T21:10:45Z","timestamp":1773090645088,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2006,4,7]],"date-time":"2006-04-07T00:00:00Z","timestamp":1144368000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2006,8]]},"DOI":"10.1007\/s00530-006-0032-2","type":"journal-article","created":{"date-parts":[[2006,4,6]],"date-time":"2006-04-06T15:04:44Z","timestamp":1144335884000},"page":"3-13","source":"Crossref","is-referenced-by-count":73,"title":["Support vector machine active learning for music retrieval"],"prefix":"10.1007","volume":"12","author":[{"given":"Michael I.","family":"Mandel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Graham E.","family":"Poliner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel P. W.","family":"Ellis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2006,4,7]]},"reference":[{"key":"32_CR1","unstructured":"All Music Guide: Site glossary. Url http:\/\/www.all-music.com\/cg\/amg.dll?p=amg&sql=32:amg\/info_pages\/a_siteglossary.html"},{"key":"32_CR2","first-page":"1","volume":"1","author":"J.J. Aucouturier","year":"2004","unstructured":"Aucouturier, J.J., Pachet, F.: Improving timbre similarity: How high's the sky? J. Negative Results Speech Audio Sci. 1(1), (2004)","journal-title":"J. Negative Results Speech Audio Sci."},{"key":"32_CR3","unstructured":"Berenzweig, A., Ellis, D.P.W., Lawrence, S.:Using voice segmentsto improve artist classification of music. In: Proceedings of AES International Conference on Virtual, Synthetic, and Entertainment Audio. Espoo, Finland (2002)"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Berenzweig, A., Ellis, D.P.W., Lawrence, S.: Anchor space for classification and similarity measurement of music. In: Proceedings of IEEE International Conference on Multimedia & Expo, pp. 29\u201332 (2003)","DOI":"10.1109\/ICME.2003.1220846"},{"key":"32_CR5","unstructured":"Berenzweig, A., Logan, B., Ellis, D.P.W., Whitman, B.: A large-scale evalutation of acoustic and subjective music similarity measures. In: Proceedings International Conference on Music Information Retrieval, pp. 103\u2013109 (2003)"},{"issue":"2","key":"32_CR6","first-page":"121","volume":"2","author":"C.J.C. Burgess","year":"1998","unstructured":"Burgess, C.J.C.: A tutorial on support vector machines for pattern recognition. Data Mining Knowledge Discov. 2(2), 121\u2013167 (1998)","journal-title":"Discov"},{"key":"32_CR7","unstructured":"Chang, E.Y., Tong, S., Goh, K., Chang, C.W.: Support vector machine concept-dependent active learning for image retrieval. ACM Trans. Multimedia (2005) in press"},{"key":"32_CR8","unstructured":"Chen, S., Gopalakrishnan, P.: Speaker, environment and channel change detection and clustering via the Bayesian Information Criterion. In: Proceedings of DARPA Broadcast News Transcription and Understanding Workshop (1998)"},{"key":"32_CR9","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511801389","volume-title":"An introduction to support Vector Machines: And other kernel-based learning methods","author":"N. Cristianini","year":"2000","unstructured":"Cristianini, N., Shawe-Taylor, J.: An introduction to support Vector Machines: And other kernel-based learning methods, Cambridge University Press, New York, NY (2000)"},{"key":"32_CR10","unstructured":"Downie, J.S., West, K., Ehmann, A., Vincent, E.: The 2005 music information retrieval evaluation exchange (MIREX 2005): Preliminary overview. In: Reiss, J.D., Wiggins, G.A. (eds.) Proceedings of the International Conference on Music Information Retrieval, pp. 320\u2013323 (2005)"},{"key":"32_CR11","unstructured":"Ellis, D., Berenzweig, A., Whitman, B.: The \u201cuspop2002\u201d pop music data set (2003). URL http:\/\/labrosa.ee. columbia.edu\/projects\/musicsim\/uspop2002.html"},{"key":"32_CR12","unstructured":"Ellis, D.P.W., Whitman, B., Berenzweig, A., Lawrence, S.: The quest for ground truth in musical artist similarity. In: Proceedings of the International Conference on Music Information Retrieval, pp. 170\u2013177 (2002)"},{"key":"32_CR13","unstructured":"Foote, J.T.: Content-based retrieval of music and audio. In: C.C.J.K. et al. (ed.) Proceedings Storage and Retrieval for Image and Video Databases (SPIE), vol. 3229, pp. 138\u2013147 (1997)"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Gish, H., Siu, M.H., Rohlicek, R.: Segregation of speakers for speech recognition and speaker identification. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing, pp. 873\u2013876 (1991)","DOI":"10.1109\/ICASSP.1991.150477"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Hoashi, K., Matsumoto, K., Inoue, N.: Personalization of user profiles for content-based music retrieval based on relevance feedback. In: Proceedings of ACM International Conference on Multimedia, pp. 110\u2013119. ACM Press, New York, NY (2003)","DOI":"10.1145\/957013.957040"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Hoashi, K., Zeitler, E., Inoue, N.: Implementation of relevance feedback for content-based music retrieval based on user prefences. In: International ACM SIGIR conference on Research and development in information retrieval, pp. 385\u2013386. ACM Press, New York, NY (2002)","DOI":"10.1145\/564376.564456"},{"key":"32_CR17","unstructured":"Ihler, A.: Kernel density estimation toolbox for MATLAB (2005)URL http:\/\/ssg.mit.edu\/~ihler\/code\/"},{"key":"32_CR18","unstructured":"Jaakkola, T.S., Haussler, D.: Exploiting generative models in discriminative classifiers. In: Advances in Neural Information Processing Systems, pp. 487\u2013493. MIT Press, Cambridge, MA (1999)"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Lai, W.C., Goh, K., Chang, E.Y.: On scalability of active learning for formulating query concepts. In: Amsaleg, L., J\u00f3nsson, B.T., Oria, V. (eds.) Workshop on Computer Vision Meets Databases, CVDB, pp. 11\u201318. ACM (2004)","DOI":"10.1145\/1039470.1039477"},{"key":"32_CR20","unstructured":"Logan, B.: Mel frequency cepstral coefficients for music modelling. In: Proceedings of the International Conference on Music Information Retrieval, pp. 33\u201345 (2000)"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Logan, B., Salomon, A.: A music similarity function based on signal analysis. In: Proceedings of IEEE International Conference on Multimedia & Expo. Tokyo, Japan, pp. 745\u2013748 (2001)","DOI":"10.1109\/ICME.2001.1237829"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Moreno, P., Rifkin, R.: Using the fisher kernel for web audio classification. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing, pp. 2417\u20132420 (2000)","DOI":"10.1109\/ICASSP.2000.859329"},{"key":"32_CR23","unstructured":"Moreno, P.J., Ho, P.P., Vasconcelos, N.: A kullback-leibler divergence based kernel for SVM classification in multimedia applications. In: Thrun, S., Saul, L., Sch\u00f6lkopf, B. (eds.) Advances in Neural Information Processing Systems. MIT Press, Cambridge, MA (2004)"},{"key":"32_CR24","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1121\/1.1911395","volume":"45","author":"A.V. Oppenheim","year":"1969","unstructured":"Oppenheim, A.V.: A speech analysis-synthesis system based on homomorphic filtering. J. Acoust. Soc. Am. 45, 458\u2013465 (1969)","journal-title":"J. Acoust. Soc. Am."},{"key":"32_CR25","unstructured":"Penny, W.D.: Kullback-Liebler divergences of normal, gamma, Dirichlet and Wishart densities. Technical report, Wellcome Department of Cognitive Neurology (2001)"},{"key":"32_CR26","unstructured":"Platt, J.C., Cristianini, N., Shawe-Taylor, J.: Large margin DAGs for multiclass classification. In: Solla, S., Leen, T., Mueller, K.R. (eds.) Advances in Neural Information Processing Systems, pp. 547\u2013553 (2000)"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Tong, S., Chang, E.: Support vector machine active learning for image retrieval. In: Proceedings of ACM International Conference on Multimedia, pp. 107\u2013118. ACM Press, New York, NY (2001)","DOI":"10.1145\/500141.500159"},{"key":"32_CR28","unstructured":"Tong, S., Koller, D.: Support vector machine active learning with applications to text classification. In: Proceedings of the International Conference on Machine Learning, pp. 999\u20131006 (2000)"},{"key":"32_CR29","first-page":"45","volume":"2","author":"S. Tong","year":"2001","unstructured":"Tong, S., Koller, D.: Support vector machine active learning with applications to text classification. J. Mach. Learning Res. 2, 45\u201366 (2001)","journal-title":"J. Mach. Learning Res."},{"issue":"5","key":"32_CR30","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/TSA.2002.800560","volume":"10","author":"G. Tzanetakis","year":"2002","unstructured":"Tzanetakis, G., Cook, P.: Musical genre classification of audio signals. IEEE Trans. Speech Audio Process. 10(5), 293\u2013302 (2002)","journal-title":"Speech Audio Process."},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Whitman, B., Flake, G., Lawrence, S.: Artist detection in music with minnowmatch. In: IEEE Workshop on Neural Networks for Signal Processing, pp. 559\u2013568. Falmouth, Massachusetts (2001)","DOI":"10.1109\/NNSP.2001.943160"},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Whitman, B., Rifkin, R.: Musical query-by-description as a multi-class learning problem. In: Proceedings of IEEE Multimedia Signal Processing Conference, pp. 153\u2013156 (2002)","DOI":"10.1109\/MMSP.2002.1203270"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-006-0032-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-006-0032-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-006-0032-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T07:38:12Z","timestamp":1736321892000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-006-0032-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,4,7]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2006,8]]}},"alternative-id":["32"],"URL":"https:\/\/doi.org\/10.1007\/s00530-006-0032-2","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,4,7]]}}}