{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T05:18:34Z","timestamp":1773033514370,"version":"3.50.1"},"publisher-location":"Cham","reference-count":9,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319224817","type":"print"},{"value":"9783319224824","type":"electronic"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-22482-4_17","type":"book-chapter","created":{"date-parts":[[2015,8,14]],"date-time":"2015-08-14T07:06:02Z","timestamp":1439535962000},"page":"143-151","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Audio-Visual Speech-Turn Detection and Tracking"],"prefix":"10.1007","author":[{"given":"Israel D.","family":"Gebru","sequence":"first","affiliation":[]},{"given":"Sil\u00e8ye","family":"Ba","sequence":"additional","affiliation":[]},{"given":"Georgios","family":"Evangelidis","sequence":"additional","affiliation":[]},{"given":"Radu","family":"Horaud","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,8,15]]},"reference":[{"issue":"2","key":"17_CR1","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 Trans. Audio Speech Lang. Process. 20(2), 356\u2013370 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Bae, S.H., Yoon, K.J.: Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning. In: Computer Vision and Pattern Recognition, pp. 1218\u20131225 (2014)","DOI":"10.1109\/CVPR.2014.159"},{"issue":"4","key":"17_CR3","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1109\/TASLP.2015.2405475","volume":"23","author":"A Deleforge","year":"2015","unstructured":"Deleforge, A., Horaud, R., Schechner, Y.Y., Girin, L.: Co-localization of audio sources in images using binaural features and locally-linear regression. IEEE Trans. Audio Speech Lang. Process. 23(4), 718\u2013731 (2015)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"2","key":"17_CR4","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. Audio Speech Lang. Process. 15(2), 601\u2013616 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"4","key":"17_CR5","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.1109\/TSP.2006.888095","volume":"55","author":"E Kidron","year":"2007","unstructured":"Kidron, E., Schechner, Y.Y., Elad, M.: Cross-modal localization via sparsity. IEEE Trans. Signal Process. 55(4), 1390\u20131404 (2007)","journal-title":"IEEE Trans. Signal Process."},{"issue":"5","key":"17_CR6","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1109\/JSTSP.2010.2057198","volume":"4","author":"S Naqvi","year":"2010","unstructured":"Naqvi, S., Yu, M., Chambers, J.: A multimodal approach to blind source separation of moving sources. IEEE J. Sel. Top. Signal Process. 4(5), 895\u2013910 (2010)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"issue":"1","key":"17_CR7","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1109\/TPAMI.2011.47","volume":"34","author":"A Noulas","year":"2012","unstructured":"Noulas, A., Englebienne, G., Krose, B.J.A.: Multimodal speaker diarization. IEEE Trans. Pattern Anal. Mach. Intell. 34(1), 79\u201393 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"9","key":"17_CR8","doi-asserted-by":"publisher","first-page":"1306","DOI":"10.1109\/JPROC.2003.817150","volume":"91","author":"G Potamianos","year":"2003","unstructured":"Potamianos, G., Neti, C., Gravier, G., Garg, A., Senior, A.W.: Recent advances in the automatic recognition of audiovisual speech. Proc. IEEE 91(9), 1306\u20131326 (2003)","journal-title":"Proc. IEEE"},{"issue":"1","key":"17_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/97.736233","volume":"6","author":"J Sohn","year":"1999","unstructured":"Sohn, J., Kim, N.S., Sung, W.: A statistical model-based voice activity detection. IEEE Signal Process. Lett. 6(1), 1\u20133 (1999)","journal-title":"IEEE Signal Process. Lett."}],"container-title":["Lecture Notes in Computer Science","Latent Variable Analysis and Signal Separation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-22482-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T06:23:28Z","timestamp":1676960608000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-22482-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319224817","9783319224824"],"references-count":9,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-22482-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"15 August 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}