{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,4]],"date-time":"2025-01-04T23:10:18Z","timestamp":1736032218503,"version":"3.32.0"},"publisher-location":"Berlin, Heidelberg","reference-count":26,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540290735"},{"type":"electronic","value":"9783540317289"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/11559887_2","type":"book-chapter","created":{"date-parts":[[2005,10,13]],"date-time":"2005-10-13T13:21:18Z","timestamp":1129209678000},"page":"22-36","source":"Crossref","is-referenced-by-count":3,"title":["Multi Channel Sequence Processing"],"prefix":"10.1007","author":[{"given":"Samy","family":"Bengio","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Herv\u00e9","family":"Bourlard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"2_CR1","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/6046.865479","volume":"2","author":"S. Dupont","year":"2000","unstructured":"Dupont, S., Luettin, J.: Audio-visual speech modeling for continuous speech recognition. IEEE Transactions on Multimedia\u00a02, 141\u2013151 (2000)","journal-title":"IEEE Transactions on Multimedia"},{"key":"2_CR2","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.inffus.2003.04.001","volume":"5","author":"S. Bengio","year":"2004","unstructured":"Bengio, S.: Multimodal speech processing using asynchronous hidden markov models. Information Fusion\u00a05, 81\u201389 (2004)","journal-title":"Information Fusion"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Morris, A., Hagen, A., Glotin, H., Bourlard, H.: Multi-stream adaptive evidence combination for noise robust ASR. Speech Communication (2001)","DOI":"10.1016\/S0167-6393(00)00044-3"},{"key":"2_CR4","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1109\/TPAMI.2005.49","volume":"27","author":"I. McCowan","year":"2005","unstructured":"McCowan, I., Gatica-Perez, D., Bengio, S., Lathoud, G., Barnard, M., Zhang, D.: Automatic analysis of multimodal group actions in meetings. IEEE Transactions on Pattern Analysis and Machine Intelligence\u00a027, 305\u2013317 (2005)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2_CR5","unstructured":"Gatica-Perez, D., Lathoud, G., McCowan, I., Odobez, J.M.: A mixed-state i-particle filter for multi-camera speaker tracking. In: Proc. of WOMTEC (2003)"},{"key":"2_CR6","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/S0167-6393(00)00020-0","volume":"32","author":"S. Renals","year":"2000","unstructured":"Renals, S., Abberley, D., Kirby, D., Robinson, T.: Indexing and retrieval of broadcast news. Speech Communication\u00a032, 5\u201320 (2000)","journal-title":"Speech Communication"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Westerveld, T., de Vries, A.P., van Ballegooij, A., de Jong, F., Hiemstra, D.: A probabilistic multimedia retrieval model and its evaluation. EURASIP Journal on Applied Signal Processing\u00a02 (2003)","DOI":"10.1155\/S111086570321101X"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Mann, S.: Smart clothing: The wearable computer and wearcam. Personal Technologies\u00a01(1) (1997)","DOI":"10.1007\/BF01317885"},{"key":"2_CR9","volume-title":"Fundamentals of Speech Recognition","author":"L.R. Rabiner","year":"1993","unstructured":"Rabiner, L.R., Juang, B.-H.: Fundamentals of Speech Recognition. Prentice-Hall, Englewood Cliffs (1993)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Boreczky, J.S., Wilcox, L.D.: A Hidden Markov Model framework for video segmentation using audio and image features. In: Proc. of ICASSP, vol.\u00a06 (1998)","DOI":"10.1109\/ICASSP.1998.679697"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Xie, L., Chang, S.F., Divakaran, A., Sun, H.: Structure analysis of soccer video with Hidden Markov Models. In: ICASSP (2002)","DOI":"10.1109\/ICASSP.2002.5745558"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Eickeler, S., M\u00fcller, S.: Content-based video indexing of TV broadcast news using Hidden Markov Models. In: Proc. of ICASSP (1999)","DOI":"10.1109\/ICASSP.1999.757471"},{"key":"2_CR13","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. Journal of Royal Statistical Society B\u00a039, 1\u201338 (1977)","journal-title":"Journal of Royal Statistical Society B"},{"key":"2_CR14","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1147\/rd.136.0675","volume":"13","author":"F. Jelinek","year":"1969","unstructured":"Jelinek, F.: A fast sequential decoding algorithm using a stack. IBM Journal of Research and Development\u00a013, 675\u2013685 (1969)","journal-title":"IBM Journal of Research and Development"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Viterbi, A.: Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Transactions on Information Theory, 260\u2013269 (1967)","DOI":"10.1109\/TIT.1967.1054010"},{"key":"2_CR16","unstructured":"Oliver, N., Horvitz, E., Garg, A.: Layered representations for learning and inferring office activity from multiple sensory channels. In: Proc. of the Int. Conf. on Multimodal Interfaces (2002)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Bourlard, H., Dupont, S.: Subband-based speech recognition. In: Proc. IEEE ICASSP (1997)","DOI":"10.1109\/ICASSP.1997.596172"},{"key":"2_CR18","volume-title":"Issues in Visual and Audio-Visual Speech Processing","author":"G. Potamianos","year":"2004","unstructured":"Potamianos, G., Neti, C., Luettin, J., Matthews, I.: Audio-visual automatic speech recognition: An overview. In: Bailly, G., Vatikiotis-Bateson, E., Perrier, P. (eds.) Issues in Visual and Audio-Visual Speech Processing. MIT Press, Cambridge (2004)"},{"key":"2_CR19","unstructured":"Brand, M.: Coupled hidden markov models for modeling interacting processes. Technical Report 405, MIT Media Lab Vision and Modeling (1996)"},{"key":"2_CR20","unstructured":"Bengio, S.: An asynchronous hidden markov model for audio-visual speech recognition. In: Becker, S., Thrun, S., Obermayer, K. (eds.) Advances in Neural Information Processing Systems, vol.\u00a015 (2003)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, D., Gatica-Perez, D., Bengio, S., McCowan, I., Lathoud, G.: Modeling individual and group actions in meetings: a two-layer hmm framework. In: IEEE Workshop on Event Mining at CVPR 2004 (2004)","DOI":"10.1109\/CVPR.2004.399"},{"key":"2_CR22","unstructured":"Bourlard, H., Bengio, S., Doss, M.M., Zhu, Q., Mesot, B., Morgan, N.: Towards using hierarchical posteriors for flexible automatic speech recognition systems. In: Proc. of DARPA EARS Rich Transcription Workshop (2004)"},{"key":"2_CR23","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","volume-title":"Neural Networks for Pattern Recognition","author":"C. Bishop","year":"1995","unstructured":"Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press, London (1995)"},{"key":"2_CR24","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y. Bengio","year":"1994","unstructured":"Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks\u00a05, 157\u2013166 (1994)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Pigeon, S., Vandendorpe, L.: The M2VTS multimodal face database (release 1.00). In: Proc. of the Conf. on AVBPA (1997)","DOI":"10.1007\/BFb0016021"},{"key":"2_CR26","unstructured":"Varga, A., Steeneken, H., Tomlinson, M., Jones, D.: The noisex-92 study on the effect of additive noise on automatic speech recognition. Technical report, DRA Speech Research Unit (1992)"}],"container-title":["Lecture Notes in Computer Science","Deterministic and Statistical Methods in Machine Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11559887_2.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,4]],"date-time":"2025-01-04T22:42:12Z","timestamp":1736030532000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11559887_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540290735","9783540317289"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/11559887_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}