{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T16:41:12Z","timestamp":1740242472281,"version":"3.37.3"},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540245094"},{"type":"electronic","value":"9783540305682"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/978-3-540-30568-2_12","type":"book-chapter","created":{"date-parts":[[2010,7,4]],"date-time":"2010-07-04T18:40:10Z","timestamp":1278268810000},"page":"136-145","source":"Crossref","is-referenced-by-count":4,"title":["Mapping from Speech to Images Using Continuous State Space Models"],"prefix":"10.1007","author":[{"given":"Tue","family":"Lehn-Schi\u00f8ler","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lars Kai","family":"Hansen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Larsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Lewis, J.P.: Automated lip-sync: Background and techniques. J. Visualization and Computer Animation\u00a02 (1991)","DOI":"10.1002\/vis.4340020404"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Goldenthal, W., Waters, K., Jean-Manuel, T.V., Glickman, O.: Driving synthetic mouth gestures: Phonetic recognition for faceme! In: Proc. Eurospeech 1997, Rhodes, Greece, pp. 1995\u20131998 (1997)","DOI":"10.21437\/Eurospeech.1997-529"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Ezzat, T., Poggio, T.: Mike talk: a talking facial display based on morphing visemes. In: Proc. Computer Animation IEEE Computer Society, pp. 96\u2013102 (1998)","DOI":"10.1109\/CA.1998.681913"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Bregler, C., Covell, M., Slaney, M.: Video rewrite: driving visual speech with audio. In: Proceedings of the 24th annual conference on Computer graphics and interactive techniques, pp. 353\u2013360. ACM Press\/Addison-Wesley Publishing Co. (1997)","DOI":"10.1145\/258734.258880"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Williams, J.J., Katsaggelos, A.K.: An hmm-based speech-to-video synthesizer. IEEE Transactions on Neural Networks\u00a013 (2002)","DOI":"10.1109\/TNN.2002.1021891"},{"key":"12_CR6","volume-title":"MPEG-4 Facial Animation: The Standard, Implementation and Applications","author":"P. Hong","year":"2002","unstructured":"Hong, P., Wen, Z., Huang, T.S.: Speech driven face animation. In: Pandzic, I.S., Forchheimer, R. (eds.) MPEG-4 Facial Animation: The Standard, Implementation and Applications, Wiley, Europe (2002)"},{"key":"12_CR7","unstructured":"Massaro, D.W., Beskow, J., Cohen, M.M., Fry, C.L., Rodriguez, T.: Picture my voice: Audio to visual speech synthesis using artificial neural networks. In: Proc. AVSP 1999 (1999)"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Brand, M.: Voice puppetry. In: Proceedings of the 26th annual conference on Computer graphics and interactive techniques, pp. 21\u201328. ACM Press\/Addison-Wesley Publishing Co. (1999)","DOI":"10.1145\/311535.311537"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Lavagetto, F.: Converting speech into lip movements: A multimedia telephone for hard of hearing people. IEEE Trans. on Rehabilitation Engineering\u00a03 (1995)","DOI":"10.1109\/86.372898"},{"key":"12_CR10","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1038\/264746a0","volume":"264","author":"H. McGurk","year":"1976","unstructured":"McGurk, H., MacDonald, J.W.: Hearing lips and seeing voices. Nature\u00a0264, 746\u2013748 (1976)","journal-title":"Nature"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Dupont, S., Luettin, J.: Audio-visual speech modelling for continuous speech recognition. IEEE Transactions on Multimedia (2000)","DOI":"10.1109\/6046.865479"},{"key":"12_CR12","doi-asserted-by":"publisher","first-page":"1975","DOI":"10.1016\/S0169-7552(98)00216-5","volume":"30","author":"D.F. McAllister","year":"1998","unstructured":"McAllister, D.F., Rodman, R.D., Bitzer, D.L., Freeman, A.S.: Speaker independence in automated lip-sync for audio-video communication. Comput. Netw. ISDN Syst.\u00a030, 1975\u20131980 (1998)","journal-title":"Comput. Netw. ISDN Syst."},{"key":"12_CR13","first-page":"484","volume":"2","author":"T. Cootes","year":"1998","unstructured":"Cootes, T., Edwards, G., Taylor, C.: Active appearance models. Proc. European Conference on Computer Vision\u00a02, 484\u2013498 (1998)","journal-title":"Proc. European Conference on Computer Vision"},{"key":"12_CR14","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1109\/34.982900","volume":"24","author":"I. Matthews","year":"2002","unstructured":"Matthews, I., Cootes, T., Bangham, J., Cox, S., Harvey, R.: Extraction of visual features for lipreading. Pattern Analysis and Machine Intelligence, IEEE Transactions on\u00a024, 198\u2013213 (2002)","journal-title":"Pattern Analysis and Machine Intelligence, IEEE Transactions on"},{"key":"12_CR15","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1109\/TMI.2003.817780","volume":"22","author":"M.B. Stegmann","year":"2003","unstructured":"Stegmann, M.B., Ersb\u00f8ll, B.K., Larsen, R.: FAME-a flexible appearance modelling environment. IEEE Transactions on Medical Imaging\u00a022, 1319\u20131331 (2003)","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"12_CR16","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1115\/1.3662552","volume":"82","author":"R.E. Kalman","year":"1960","unstructured":"Kalman, R.E.: A new approach to linear filtering and prediction problems. Transactions of the ASME\u2013Journal of Basic Engineering\u00a082, 35\u201345 (1960)","journal-title":"Transactions of the ASME\u2013Journal of Basic Engineering"},{"key":"12_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. JRSSB\u00a039, 1\u201338 (1977)","journal-title":"JRSSB"},{"key":"12_CR18","unstructured":"Ghahramani, Z., Hinton, G.: Parameter estimation for linear dynamical systems. Technical report, University of Toronto, CRG-TR-96-2 (1996)"},{"key":"12_CR19","doi-asserted-by":"publisher","first-page":"997","DOI":"10.1109\/ICIP.2002.1039143","volume":"3","author":"C. Sanderson","year":"2002","unstructured":"Sanderson, C., Paliwal, K.K.: Polynomial features for robust face authentication. Proceedings of International Conference on Image Processing\u00a03, 997\u20131000 (2002)","journal-title":"Proceedings of International Conference on Image Processing"}],"container-title":["Lecture Notes in Computer Science","Machine Learning for Multimodal Interaction"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-30568-2_12.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T16:15:29Z","timestamp":1740240929000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-30568-2_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540245094","9783540305682"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-30568-2_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}