{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T01:37:32Z","timestamp":1794533852403,"version":"4.9.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319488806","type":"print"},{"value":"9783319488813","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","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":[[2016]]},"DOI":"10.1007\/978-3-319-48881-3_57","type":"book-chapter","created":{"date-parts":[[2016,11,2]],"date-time":"2016-11-02T09:19:08Z","timestamp":1478078348000},"page":"869-882","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Speech-Driven Facial Animation Using Manifold Relevance Determination"],"prefix":"10.1007","author":[{"given":"Samia","family":"Dawood","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulia","family":"Hicks","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Marshall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,11,3]]},"reference":[{"key":"57_CR1","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3905.001.0001","volume-title":"An introduction to neural networks","author":"JA Anderson","year":"1995","unstructured":"Anderson, J.A.: An introduction to neural networks. MIT press, Cambridge (1995)"},{"key":"57_CR2","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":"57_CR3","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":"57_CR4","unstructured":"Brooke, N.M., Scott, S.D.: Two-and three-dimensional audio-visual speech synthesis. In: AVSP 1998 International Conference on Auditory-Visual Speech Processing (1998)"},{"issue":"1","key":"57_CR5","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1109\/79.911195","volume":"18","author":"T Chen","year":"2001","unstructured":"Chen, T.: Audiovisual speech processing. IEEE Signal Process. Mag. 18(1), 9\u201321 (2001)","journal-title":"IEEE Signal Process. Mag."},{"key":"57_CR6","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1109\/34.927467","volume":"6","author":"TF Cootes","year":"2001","unstructured":"Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Trans. Pattern Anal. Mach. Intell. 6, 681\u2013685 (2001)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"57_CR7","unstructured":"Cosker, D., Marshall, D., Rosin, P., Hicks, Y.: Video realistic talking heads using hierarchical non-linear speech-appearance models. In: Mirage, France, 147 (2003)"},{"key":"57_CR8","unstructured":"Damianou, A., Ek, C., Titsias, M., Lawrence, N.: Manifold relevance determination. arXiv preprint arXiv:1206.4610 (2012)"},{"key":"57_CR9","unstructured":"Damianou, A., Titsias, M.K., Lawrence, N.D.: Variational Gaussian process dynamical systems. In: Advances in Neural Information Processing Systems, pp. 2510\u20132518 (2011)"},{"key":"57_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-642-10331-5_9","volume-title":"Advances in Visual Computing","author":"S Deena","year":"2009","unstructured":"Deena, S., Galata, A.: Speech-driven facial animation using a shared Gaussian process latent variable model. In: Bebis, G., et al. (eds.) ISVC 2009, Part I. LNCS, vol. 5875, pp. 89\u2013100. Springer, Heidelberg (2009)"},{"key":"57_CR11","doi-asserted-by":"crossref","unstructured":"Deena, S., Hou, S., Galata, A.: Visual speech synthesis by modelling coarticulation dynamics using a non-parametric switching state-space model. In: International Conference on Multimodal Interfaces and the Workshop on Machine Learning for Multimodal Interaction, pp. 1\u20138. ACM (2010)","DOI":"10.1145\/1891903.1891942"},{"issue":"8","key":"57_CR12","doi-asserted-by":"publisher","first-page":"1755","DOI":"10.1109\/TMM.2013.2279659","volume":"15","author":"S Deena","year":"2013","unstructured":"Deena, S., Hou, S., Galata, A.: Visual speech synthesis using a variable-order switching shared Gaussian process dynamical model. IEEE Trans. Multimedia 15(8), 1755\u20131768 (2013)","journal-title":"IEEE Trans. Multimedia"},{"key":"57_CR13","unstructured":"Deena, S.P.: Visual speech synthesis by learning joint probabilistic models of audio and video (2012)"},{"key":"57_CR14","first-page":"147","volume":"1107","author":"CH Ek","year":"2009","unstructured":"Ek, C.H., Jaeckel, P., Campbell, N., Lawrence, N.D., Melhuish, C.: Shared gaussian process latent variable models for handling ambiguous facial expressions. Am. Inst. Phys. Conf. Ser. 1107, 147\u2013153 (2009)","journal-title":"Am. Inst. Phys. Conf. Ser."},{"key":"57_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1007\/978-3-540-85853-9_6","volume-title":"Machine Learning for Multimodal Interaction","author":"CH Ek","year":"2008","unstructured":"Ek, C.H., Rihan, J., Torr, P.H.S., Rogez, G., Lawrence, N.D.: Ambiguity modeling in latent spaces. In: Popescu-Belis, A., Stiefelhagen, R. (eds.) MLMI 2008. LNCS, vol. 5237, pp. 62\u201373. Springer, Heidelberg (2008). doi: 10.1007\/978-3-540-85853-9_6"},{"key":"57_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1007\/978-3-540-78155-4_12","volume-title":"Machine Learning for Multimodal Interaction","author":"CH Ek","year":"2008","unstructured":"Ek, C.H., Torr, P.H.S., Lawrence, N.D.: Gaussian process latent variable models for human pose estimation. In: Popescu-Belis, A., Renals, S., Bourlard, H. (eds.) MLMI 2007. LNCS, vol. 4892, pp. 132\u2013143. Springer, Heidelberg (2008). doi: 10.1007\/978-3-540-78155-4_12"},{"key":"57_CR17","unstructured":"Englebienne, G.: Animating faces from speech. Ph.D. thesis, Citeseer (2008)"},{"issue":"1","key":"57_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.image.2005.04.002","volume":"21","author":"CK Hsieh","year":"2006","unstructured":"Hsieh, C.K., Chen, Y.C.: Partial linear regression for speech-driven talking head application. Signal Proces. Image Commun. 21(1), 1\u201312 (2006)","journal-title":"Signal Proces. Image Commun."},{"issue":"2","key":"57_CR19","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/S0095-4470(19)31123-4","volume":"5","author":"RD Kent","year":"1977","unstructured":"Kent, R.D., Minifie, F.D.: Coarticulation in recent speech production models. J. Phonetics 5(2), 115\u2013133 (1977)","journal-title":"J. Phonetics"},{"key":"57_CR20","first-page":"1783","volume":"6","author":"N Lawrence","year":"2005","unstructured":"Lawrence, N.: Probabilistic non-linear principal component analysis with Gaussian process latent variable models. J. Mach. Learn. Res. 6, 1783\u20131816 (2005)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"57_CR21","first-page":"329","volume":"16","author":"ND Lawrence","year":"2004","unstructured":"Lawrence, N.D.: Gaussian process latent variable models for visualisation of high dimensional data. Adv. Neural Inf. Process. Syst. 16(3), 329\u2013336 (2004)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"57_CR22","doi-asserted-by":"crossref","unstructured":"Lawrence, N.D.: Learning for larger datasets with the Gaussian process latent variable model. In: International Conference on Artificial Intelligence and Statistics, pp. 243\u2013250 (2007)","DOI":"10.1145\/1273496.1273557"},{"key":"57_CR23","unstructured":"Massaro, D.W., Beskow, J., Cohen, M.M., Fry, C.L., Rodgriguez, T.: Picture my voice: audio to visual speech synthesis using artificial neural networks. In: AVSP 1999-International Conference on Auditory-Visual Speech Processing (1999)"},{"key":"57_CR24","unstructured":"Parke, F.I.: A parametric model for human faces. Technical report, DTIC Document (1974)"},{"key":"57_CR25","doi-asserted-by":"crossref","unstructured":"Rasmussen, C.E.: Gaussian processes for machine learning (2006)","DOI":"10.7551\/mitpress\/3206.001.0001"},{"issue":"2\u20133","key":"57_CR26","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1023\/A:1026490906255","volume":"25","author":"D Ron","year":"1996","unstructured":"Ron, D., Singer, Y., Tishby, N.: The power of Amnesia: learning probabilistic automata with variable memory length. Mach. Learn. 25(2\u20133), 117\u2013149 (1996)","journal-title":"Mach. Learn."},{"key":"57_CR27","unstructured":"Salzmann, M., Ek, C.H., Urtasun, R., Darrell, T.: Factorized orthogonal latent spaces. In: International Conference on Artificial Intelligence and Statistics, pp. 701\u2013708 (2010)"},{"key":"57_CR28","unstructured":"Shon, A., Grochow, K., Hertzmann, A., Rao, R.P.: Learning shared latent structure for image synthesis and robotic imitation. In: Advances in Neural Information Processing Systems, pp. 1233\u20131240 (2005)"},{"issue":"4","key":"57_CR29","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1016\/S0923-5965(99)00055-7","volume":"15","author":"AM Tekalp","year":"2000","unstructured":"Tekalp, A.M., Ostermann, J.: Face and 2-D mesh animation in MPEG-4. Signal Process. Image Commun. 15(4), 387\u2013421 (2000)","journal-title":"Signal Process. Image Commun."},{"key":"57_CR30","doi-asserted-by":"crossref","unstructured":"Theobald, B.J.: Visual speech synthesis using shape and appearance models. Ph.D. thesis, University of East Anglia (2003)","DOI":"10.5244\/C.17.3"},{"key":"57_CR31","doi-asserted-by":"crossref","unstructured":"Theobald, B.J., Fagel, S., Bailly, G., Elisei, F.: Lips 2008: visual speech synthesis challenge. In: Interspeech, pp. 2310\u20132313 (2008)","DOI":"10.21437\/Interspeech.2008-590"},{"key":"57_CR32","unstructured":"Theobald, B.J., Wilkinson, N.: A real-time speech-driven talking head using active appearance models. In: AVSP, pp. 264\u2013269 (2007)"},{"key":"57_CR33","unstructured":"Titsias, M.K.: Variational learning of inducing variables in sparse gaussian processes. In: International Conference on Artificial Intelligence and Statistics, pp. 567\u2013574 (2009)"},{"key":"57_CR34","unstructured":"Titsias, M.K., Lawrence, N.D.: Bayesian Gaussian process latent variable model. In: International Conference on Artificial Intelligence and Statistics, pp. 844\u2013851 (2010)"},{"key":"57_CR35","unstructured":"Wang, J., Hertzmann, A., Blei, D.M.: Gaussian process dynamical models. In: Advances in neural information processing systems, pp. 1441\u20131448 (2005)"},{"key":"57_CR36","doi-asserted-by":"crossref","unstructured":"Wang, L., Qian, X., Han, W., Soong, F.K.: Photo-real lips synthesis with trajectory-guided sample selection. In: SSW, pp. 217\u2013222 (2010)","DOI":"10.21437\/Interspeech.2010-194"},{"issue":"3","key":"57_CR37","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1109\/TVCG.2004.1272733","volume":"10","author":"Y Zhang","year":"2004","unstructured":"Zhang, Y., Prakash, E.C., Sung, E.: A new physical model with multilayer architecture for facial expression animation using dynamic adaptive mesh. IEEE Trans. Visual. Comput. Graphics 10(3), 339\u2013352 (2004)","journal-title":"IEEE Trans. Visual. Comput. Graphics"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016 Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-48881-3_57","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T21:53:45Z","timestamp":1657576425000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-48881-3_57"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319488806","9783319488813"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-48881-3_57","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-3-319-48881-3","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"3 November 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}