{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T17:10:07Z","timestamp":1746378607670,"version":"3.40.4"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319125671"},{"type":"electronic","value":"9783319125688"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-662-44654-6_5","type":"book-chapter","created":{"date-parts":[[2014,9,15]],"date-time":"2014-09-15T01:13:21Z","timestamp":1410743601000},"page":"50-59","source":"Crossref","is-referenced-by-count":0,"title":["Utilising Tree-Based Ensemble Learning for Speaker Segmentation"],"prefix":"10.1007","author":[{"given":"Mohamed","family":"Abou-Zleikha","sequence":"first","affiliation":[]},{"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[]},{"given":"Mads Gr\u00e6sb\u00f8ll","family":"Christensen","sequence":"additional","affiliation":[]},{"given":"S\u00f8ren Holdt","family":"Jensen","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Abou-Zleikha, M., , Tan, Z.H., Christensen, M.G., Jensen, S.H.: Non-linguistic vocal event detection and localisation using online random forest. In: Proceedings of 37th International Convention of Information and Communication Technology (MIPRO). IEEE (2014)","DOI":"10.1109\/MIPRO.2014.6859773"},{"issue":"8","key":"5_CR2","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1109\/LSP.2004.831666","volume":"11","author":"J. Ajmera","year":"2004","unstructured":"Ajmera, J., McCowan, I., Bourlard, H.: Robust speaker change detection. IEEE Signal Processing Letters\u00a011(8), 649\u2013651 (2004)","journal-title":"IEEE Signal Processing Letters"},{"issue":"2","key":"5_CR3","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1109\/TASL.2011.2125954","volume":"20","author":"X. Anguera Miro","year":"2012","unstructured":"Anguera Miro, X., Bozonnet, S., Evans, N., Fredouille, C., Friedland, G., Vinyals, O.: Speaker diarization: A review of recent research. IEEE Transactions on Audio, Speech, and Language Processing\u00a020(2), 356\u2013370 (2012)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Ben, M., Betser, M., Bimbot, F., Gravier, G.: Speaker diarization using bottom-up clustering based on a parameter-derived distance between adapted gmms. In: Proceedings of ICSLP (2004)","DOI":"10.21437\/Interspeech.2004-523"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Bonastre, J.F., Delacourt, P., Fredouille, C., Merlin, T., Wellekens, C.: A speaker tracking system based on speaker turn detection for nist evaluation. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, vol.\u00a02, pp. II1177\u2013II1180. IEEE (2000)","DOI":"10.1109\/ICASSP.2000.859175"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Breiman, L.: Random forests. Machine learning 45(1), 5\u201332 (2001)","DOI":"10.1023\/A:1010933404324"},{"key":"5_CR7","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)"},{"issue":"1","key":"5_CR8","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/TASL.2009.2024730","volume":"18","author":"S.S. Cheng","year":"2010","unstructured":"Cheng, S.S., Wang, H.M., Fu, H.C.: Bic-based speaker segmentation using divide-and-conquer strategies with application to speaker diarization. IEEE Transactions on Audio, Speech, and Language Processing\u00a018(1), 141\u2013157 (2010)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"6","key":"5_CR9","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1049\/iet-spr.2009.0235","volume":"4","author":"M. Gra\u0161i\u010d","year":"2010","unstructured":"Gra\u0161i\u010d, M., Kos, M., Ka\u010di\u010d, Z.: Online speaker segmentation and clustering using cross-likelihood ratio calculation with reference criterion selection. IET signal processing\u00a04(6), 673\u2013685 (2010)","journal-title":"IET signal processing"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Kotti, M., Benetos, E., Kotropoulos, C.: Automatic speaker change detection with the bayesian information criterion using mpeg-7 features and a fusion scheme. In: IEEE International Symposium on Circuits and Systems, p. 4. IEEE (2006)","DOI":"10.1109\/ISCAS.2006.1692970"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Kumar, A., Dighe, P., Singh, R., Chaudhuri, S., Raj, B.: Audio event detection from acoustic unit occurrence patterns. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 489\u2013492 (2012)","DOI":"10.1109\/ICASSP.2012.6287923"},{"key":"5_CR12","unstructured":"Lamel, L.F., Kassel, R.H., Seneff, S.: Speech database development: Design and analysis of the acoustic-phonetic corpus. In: Speech Input\/Output Assessment and Speech Databases (1989)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Li, R., Schultz, T., Jin, Q.: Improving speaker segmentation via speaker identification and text segmentation. In: Proceedings of INTERSPEECH 2009 (2009)","DOI":"10.21437\/Interspeech.2009-272"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Meinedo, H., Neto, J.: Audio segmentation, classification and clustering in a broadcast news task. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, vol.\u00a02, pp. II\u20135. IEEE (2003)","DOI":"10.1109\/ICASSP.2003.1202280"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Mohammadi, S.H., Sameti, H., Langarani, M.S.E., Tavanaei, A.: Knndist: A non-parametric distance measure for speaker segmentation. In: Proceedings of INTERSPEECH (2012)","DOI":"10.21437\/Interspeech.2012-599"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Mori, K., Nakagawa, S.: Speaker change detection and speaker clustering using vq distortion for broadcast news speech recognition. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, vol.\u00a01, pp. 413\u2013416. IEEE (2001)","DOI":"10.1109\/ICASSP.2001.940855"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Moschou, V., Kotti, M., Benetos, E., Kotropoulos, C.: Systematic comparison of bic-based speaker segmentation systems. In: Proceedings of IEEE 9th Workshop on Multimedia Signal Processing, pp. 66\u201369. IEEE (2007)","DOI":"10.1109\/MMSP.2007.4412819"},{"issue":"3","key":"5_CR18","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/j.ipm.2008.09.003","volume":"45","author":"J. Rong","year":"2009","unstructured":"Rong, J., Li, G., Chen, Y.P.P.: Acoustic feature selection for automatic emotion recognition from speech. Information processing & management\u00a045(3), 315\u2013328 (2009)","journal-title":"Information processing & management"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Schuller, B., Batliner, A., Seppi, D., Steidl, S., Vogt, T., Wagner, J., Devillers, L., Vidrascu, L., Amir, N., Kessous, L., et al.: The relevance of feature type for the automatic classification of emotional user states: low level descriptors and functionals. In: Proceedings of INTERSPEECH, vol.\u00a02007, pp. 1\u20134 (2007)","DOI":"10.21437\/Interspeech.2007-612"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Tritschler, A., Gopinath, R.A.: Improved speaker segmentation and segments clustering using the bayesian information criterion. In: Proceedings of Eurospeech, vol.\u00a099, pp. 679\u2013682 (1999)","DOI":"10.21437\/Eurospeech.1999-174x"},{"key":"5_CR21","unstructured":"Vandecatseye, A., Martens, J.P., Neto, J.P., Meinedo, H., Garcia-Mateo, C., Dieguez-Tirado, J., Mihelic, F., Zibert, J., Nouza, J., David, P., et al.: The cost278 pan-european broadcast news database. In: Proceedings of LREC (2004)"}],"container-title":["Lecture Notes in Computer Science","Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-44654-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T16:32:19Z","timestamp":1746376339000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-662-44654-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319125671","9783319125688"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-44654-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}