{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:14:20Z","timestamp":1775837660304,"version":"3.50.1"},"reference-count":21,"publisher":"Elsevier BV","issue":"5","license":[{"start":{"date-parts":[[2001,4,1]],"date-time":"2001-04-01T00:00:00Z","timestamp":986083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Pattern Recognition Letters"],"published-print":{"date-parts":[[2001,4]]},"DOI":"10.1016\/s0167-8655(00)00119-7","type":"journal-article","created":{"date-parts":[[2002,7,25]],"date-time":"2002-07-25T08:02:47Z","timestamp":1027584167000},"page":"533-544","source":"Crossref","is-referenced-by-count":179,"title":["Classification of general audio data for content-based retrieval"],"prefix":"10.1016","volume":"22","author":[{"given":"Dongge","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ishwar K.","family":"Sethi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nevenka","family":"Dimitrova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"McGee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0167-8655(00)00119-7_BIB1","doi-asserted-by":"crossref","unstructured":"Patel, N.V., Sethi, I.K., 1996. Audio characterization for video indexing. In: Proc. IS & T\/SPIE Conf. Storage and Retrieval for Image and Video Databases IV, San Jose, CA, February, pp. 373\u2013384","DOI":"10.1117\/12.234776"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB2","doi-asserted-by":"crossref","unstructured":"Patel, N.V., Sethi, I.K., 1997. Video Classification using Speaker Identification. In: Proc. IS & T\/SPIE Conf. Storage and Retrieval for Image and Video Databases V, San Jose, CA, February, pp. 218\u2013225","DOI":"10.1117\/12.263411"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB3","doi-asserted-by":"crossref","unstructured":"Saraceno, C., Leonardi, R., 1997. Identification of successive correlated camera shots using audio and video information. Proc. ICIP'97 3, 166\u2013169","DOI":"10.1109\/ICIP.1997.632039"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB4","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y., Chen, T., 1998. Audio feature extraction and analysis for scene classification. J. VLSI Signal Processing (Special issue on multimedia signal processing) October, 61\u201379","DOI":"10.1023\/A:1008066223044"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB5","doi-asserted-by":"crossref","unstructured":"Spina, M., Zue, V.W., 1996. Automatic transcription of general audio data: preliminary analyses. In: Proc. International Conference on Spoken Language Processing, Philadelphia, PA, October, pp. 594\u2013597","DOI":"10.1109\/ICSLP.1996.607431"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB6","unstructured":"Gopalakrishnan, et al. P.S., 1996. Transcription of radio broadcast news with the IBM large vocabulary speech recognition system. In: Proc. DARPA Speech Recognition Workshop, February"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB7","doi-asserted-by":"crossref","unstructured":"Hansen, J.H.L., Womack, B.D., 1996. Feature analysis and neural network-based classification of speech under stress. IEEE Trans. Speech Audio Processing 4(4), 307\u2013313","DOI":"10.1109\/89.506935"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB8","doi-asserted-by":"crossref","unstructured":"Zhang, T., Kuo, C.-C.J., 1999. Audio-guided audiovisual data segmentation, indexing, and retrieval. In: IS & T\/SPIE's Symposium on Electronic Imaging Science & Technology \u2013 Conference on Storage and Retrieval for Image and Video Databases VII, SPIE 3656, San Jose, CA, January, pp. 316\u2013327","DOI":"10.1117\/12.333851"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB9","unstructured":"Kimber, D., Wilcox, L., 1996. Acoustic segmentation for audio browsers. In: Proc. Interface Conference, Sydney, Australia, July"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB10","unstructured":"Li, D., Dimitrova, N., 1997. Tools for audio analysis and classification. Philips Technical Report, August"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB11","doi-asserted-by":"crossref","unstructured":"Wold, E., Blum, et al. T., 1996. Content-based classification, search, and retrieval of audio. IEEE Multimedia, Fall, 27\u201336","DOI":"10.1109\/93.556537"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB12","doi-asserted-by":"crossref","unstructured":"Pfeiffer, S., Fischer, S., Effelsberg, W., 1996. Automatic audio content analysis. In: Proc. of ACM Multimedia'96, Boston, MA, pp. 21\u201330","DOI":"10.1145\/244130.244139"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB13","doi-asserted-by":"crossref","unstructured":"Fischer, S., Lienhart, R., Effelsberg, W., 1995. Automatic recognition of film genres. In: Proc. of ACM Multimedia'95, San Francisco, CA, 295\u2013304","DOI":"10.1145\/217279.215283"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB14","doi-asserted-by":"crossref","unstructured":"Scheirer, E., Slaney, M., 1997. Construction and evaluation of a robust multifeature speech\/music discriminator. In: Proc. ICASSP'97, Munich, Germany, April, pp. 1331\u20131334","DOI":"10.1109\/ICASSP.1997.596192"},{"issue":"1","key":"10.1016\/S0167-8655(00)00119-7_BIB15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/j.1538-7305.1965.tb04135.x","article-title":"A technique for investigating on-off patterns of speech","volume":"44","author":"Brady","year":"1965","journal-title":"The Bell Syst. Tech. J."},{"issue":"4","key":"10.1016\/S0167-8655(00)00119-7_BIB16","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1109\/TPAMI.1982.4767278","article-title":"Hierarchical classifier design using mutual information","volume":"4","author":"Sethi","year":"1982","journal-title":"IEEE Trans. Pattern Recognition Machine Intelligence"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB17","series-title":"Pattern Classification and Scene Analysis","author":"Duda","year":"1973"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB18","unstructured":"Agnello, J.G., 1963. A study of intra- and inter-phrasal pauses and their relationship to the rate of speech. Ohio State University Ph.D. Thesis"},{"key":"10.1016\/S0167-8655(00)00119-7_BIB19","doi-asserted-by":"crossref","unstructured":"Ghias, et al. A., 1995. Query by humming. In: Proc. ACM Multimedia'95, San Francisco, pp. CA, 231\u2013236","DOI":"10.1145\/217279.215273"},{"issue":"2","key":"10.1016\/S0167-8655(00)00119-7_BIB20","doi-asserted-by":"crossref","DOI":"10.1121\/1.1910339","article-title":"Cepstrum pitch determination","volume":"41","author":"Noll","year":"1967","journal-title":"J. Acoust. Soc. Amer."},{"issue":"2","key":"10.1016\/S0167-8655(00)00119-7_BIB21","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1109\/89.366548","article-title":"A comparative study of robust linear predictive analysis methods with applications to speaker identification","volume":"3","author":"Ramachandran","year":"1995","journal-title":"IEEE Trans. Speech Audio Processing"}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865500001197?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865500001197?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T04:25:06Z","timestamp":1733199906000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167865500001197"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,4]]},"references-count":21,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2001,4]]}},"alternative-id":["S0167865500001197"],"URL":"https:\/\/doi.org\/10.1016\/s0167-8655(00)00119-7","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2001,4]]}}}