{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T05:27:08Z","timestamp":1738387628618,"version":"3.35.0"},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540858522"},{"type":"electronic","value":"9783540858539"}],"license":[{"start":{"date-parts":[[2008,1,1]],"date-time":"2008-01-01T00:00:00Z","timestamp":1199145600000},"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":[[2008]]},"DOI":"10.1007\/978-3-540-85853-9_8","type":"book-chapter","created":{"date-parts":[[2008,8,30]],"date-time":"2008-08-30T09:27:54Z","timestamp":1220088474000},"page":"86-97","source":"Crossref","is-referenced-by-count":8,"title":["Audio-Visual Clustering for 3D Speaker Localization"],"prefix":"10.1007","author":[{"given":"Vasil","family":"Khalidov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florence","family":"Forbes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miles","family":"Hansard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elise","family":"Arnaud","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radu","family":"Horaud","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"8_CR1","doi-asserted-by":"publisher","first-page":"1260","DOI":"10.1155\/S1110865702206150","volume":"11","author":"M. Heckmann","year":"2002","unstructured":"Heckmann, M., Berthommier, F., Kroschel, K.: Noise adaptive stream weighting in audio-visual speech recognition. EURASIP J. Applied Signal Proc.\u00a011, 1260\u20131273 (2002)","journal-title":"EURASIP J. Applied Signal Proc."},{"issue":"7","key":"8_CR2","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1109\/TPAMI.2003.1206512","volume":"25","author":"M. Beal","year":"2003","unstructured":"Beal, M., Jojic, N., Attias, H.: A graphical model for audiovisual object tracking. IEEE Trans. PAMI\u00a025(7), 828\u2013836 (2003)","journal-title":"IEEE Trans. PAMI"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Kushal, A., Rahurkar, M., Fei-Fei, L., Ponce, J., Huang, T.: Audio-visual speaker localization using graphical models. In: Proc.18th Int. Conf. Pat. Rec., pp. 291\u2013294 (2006)","DOI":"10.1109\/ICPR.2006.284"},{"key":"8_CR4","doi-asserted-by":"publisher","first-page":"1154","DOI":"10.1155\/S1110865702206058","volume":"11","author":"D.N. Zotkin","year":"2002","unstructured":"Zotkin, D.N., Duraiswami, R., Davis, L.S.: Joint audio-visual tracking using particle filters. EURASIP Journal on Applied Signal Processing\u00a011, 1154\u20131164 (2002)","journal-title":"EURASIP Journal on Applied Signal Processing"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Vermaak, J., Ganget, M., Blake, A., P\u00e9rez, P.: Sequential monte carlo fusion of sound and vision for speaker tracking. In: Proc. 8th Int. Conf. Comput. Vision, pp. 741\u2013746 (2001)","DOI":"10.1109\/ICCV.2001.937600"},{"key":"8_CR6","first-page":"495","volume":"92","author":"P. Perez","year":"2004","unstructured":"Perez, P., Vermaak, J., Blake, A.: Data fusion for visual tracking with particles. Proc. of IEEE (spec. issue on Sequential State Estimation)\u00a092, 495\u2013513 (2004)","journal-title":"Proc. of IEEE (spec. issue on Sequential State Estimation)"},{"key":"8_CR7","first-page":"485","volume":"92","author":"Y. Chen","year":"2004","unstructured":"Chen, Y., Rui, Y.: Real-time speaker tracking using particle filter sensor fusion. Proc. of IEEE (spec. issue on Sequential State Estimation)\u00a092, 485\u2013494 (2004)","journal-title":"Proc. of IEEE (spec. issue on Sequential State Estimation)"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Nickel, K., Gehrig, T., Stiefelhagen, R., McDonough, J.: A joint particle filter for audio-visual speaker tracking. In: ICMI 2005, pp. 61\u201368 (2005)","DOI":"10.1145\/1088463.1088477"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Checka, N., Wilson, K., Siracusa, M., Darrell, T.: Multiple person and speaker activity tracking with a particle filter. In: IEEE Conf. Acou. Spee. Sign. Proc., pp. 881\u2013884 (2004)","DOI":"10.1109\/ICASSP.2004.1327252"},{"issue":"2","key":"8_CR10","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1109\/TASL.2006.881678","volume":"15","author":"D. Gatica-Perez","year":"2007","unstructured":"Gatica-Perez, D., Lathoud, G., Odobez, J.-M., McCowan, I.: Audiovisual probabilistic tracking of multiple speakers in meetings. IEEE trans. Audi. Spee. Lang. Proc.\u00a015(2), 601\u2013616 (2007)","journal-title":"IEEE trans. Audi. Spee. Lang. Proc."},{"issue":"3","key":"8_CR11","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1109\/TMM.2004.827503","volume":"6","author":"J. Fisher","year":"2004","unstructured":"Fisher, J., Darrell, T.: Speaker association with signal-level audiovisual fusion. IEEE Trans. on Multimedia\u00a06(3), 406\u2013413 (2004)","journal-title":"IEEE Trans. on Multimedia"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Barzelay, Z., Schechner, Y.Y.: Harmony in motion. In: IEEE Conf. Comput. Vision Pat. Rec (CVPR), pp. 1\u20138 (2007)","DOI":"10.1109\/CVPR.2007.383344"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Christensen, H., Ma, N., Wrigley, S.N., Barker, J.: Integrating pitch and localisation cues at a speech fragment level. In: Proc. of Interspeech 2007, pp. 2769\u20132772 (2007)","DOI":"10.21437\/Interspeech.2007-464"},{"key":"8_CR14","series-title":"NATO ASI Series","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1007\/978-3-662-13015-5_36","volume-title":"Speechreading by Humans and Machines: Models, Systems and Applications","author":"J.R. Movellan","year":"1996","unstructured":"Movellan, J.R., Chadderdon, G.: Channel separability in the audio-visual integration of speech: A bayesian approach. In: Stork, D.G., Hennecke, M.E. (eds.) Speechreading by Humans and Machines: Models, Systems and Applications. NATO ASI Series, pp. 473\u2013487. Springer, Berlin (1996)"},{"issue":"3","key":"8_CR15","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1511\/1998.25.861","volume":"86","author":"D.W. Massaro","year":"1998","unstructured":"Massaro, D.W., Stork, D.G.: Speech recognition and sensory integration. American Scientist\u00a086(3), 236\u2013244 (1998)","journal-title":"American Scientist"},{"key":"8_CR16","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/S0031-3203(02)00027-4","volume":"36","author":"G. Celeux","year":"2003","unstructured":"Celeux, G., Forbes, F., Peyrard, N.: EM procedures using mean-field approximations for Markov model-based image segmentation. Pattern Recognition\u00a036, 131\u2013144 (2003)","journal-title":"Pattern Recognition"},{"issue":"1","key":"8_CR17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A.P. Dempster","year":"1977","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm (with discussion). J. Roy. Statist. Soc. Ser. B\u00a039(1), 1\u201338 (1977)","journal-title":"J. Roy. Statist. Soc. Ser. B"},{"issue":"2","key":"8_CR18","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1214\/aos\/1176344136","volume":"6","author":"G. Schwarz","year":"1978","unstructured":"Schwarz, G.: Estimating the dimension of a model. The Annals of Statistics\u00a06(2), 461\u2013464 (1978)","journal-title":"The Annals of Statistics"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Harris, C., Stephens, M.: A combined corner and edge detector. In: Proc. 4th Alvey Vision Conference, pp. 147\u2013151 (1988)","DOI":"10.5244\/C.2.23"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Hansard, M., Horaud, R.P.: Patterns of binocular disparity for a fixating observer. In: Adv. Brain Vision Artif. Intel., 2nd Int. Symp., pp. 308\u2013317 (2007)","DOI":"10.1007\/978-3-540-75555-5_29"},{"key":"8_CR21","unstructured":"Intel OpenCV Computer Vision library, http:\/\/www.intel.com\/technology\/computing\/opencv"},{"issue":"2","key":"8_CR22","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P. Viola","year":"2004","unstructured":"Viola, P., Jones, M.: Robust real-time face detection. IJCV\u00a057(2), 137\u2013154 (2004)","journal-title":"IJCV"}],"container-title":["Lecture Notes in Computer Science","Machine Learning for Multimodal Interaction"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-85853-9_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T19:05:36Z","timestamp":1738350336000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-85853-9_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008]]},"ISBN":["9783540858522","9783540858539"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-85853-9_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2008]]}}}