{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T22:09:22Z","timestamp":1769638162598,"version":"3.49.0"},"publisher-location":"Berlin, Heidelberg","reference-count":87,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642005244","type":"print"},{"value":"9783642005251","type":"electronic"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-00525-1_1","type":"book-chapter","created":{"date-parts":[[2009,2,16]],"date-time":"2009-02-16T13:50:22Z","timestamp":1234792222000},"page":"1-23","source":"Crossref","is-referenced-by-count":9,"title":["Multimodal Human Machine Interactions in Virtual and Augmented Reality"],"prefix":"10.1007","author":[{"given":"G\u00e9rard","family":"Chollet","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Esposito","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Annie","family":"Gentes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Horain","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Walid","family":"Karam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenbo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Catherine","family":"Pelachaud","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Perrot","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dijana","family":"Petrovska-Delacr\u00e9taz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dianle","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leila","family":"Zouari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"1_CR1","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1007\/978-3-540-71505-4_8","volume-title":"Progress in Non-Linear Speech Processing","author":"B. Abboud","year":"2007","unstructured":"Abboud, B., Bredin, H., Aversano, G., Chollet, G.: Audio-visual identity verification: an introductory overview. In: Stylianou, Y. (ed.) Progress in Non-Linear Speech Processing, pp. 118\u2013134. Springer, Heidelberg (2007)"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Abe, M., Nakamura, S., Shikano, K., Kuwabara, H.: Voice conversion through vector quantization. In: International Conference on Acoustics, Speech, and Signal Processing (1988)","DOI":"10.1109\/ICASSP.1988.196671"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Agarwal, A., Triggs, B.: Recovering 3D human pose from monocular images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44\u201358 (2006)","DOI":"10.1109\/TPAMI.2006.21"},{"key":"1_CR4","unstructured":"Ahlberg, J.: Candide-3, an updated parameterized face. Technical report, Link\u00f6ping University, Sweden (2001)"},{"key":"1_CR5","unstructured":"Ahlberg, J.: Real-time facial feature tracking using an active model with fast image warping. In: International Workshop on Very Low Bitrates Video (2001)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Albrecht, I., Schroeder, M., Haber, J., Seidel, H.-P.: Mixed feelings \u2013 expression of non-basic emotions in a muscle-based talking head. In: Virtual Reality (Special Issue Language, Speech and Gesture for VR) (2005)","DOI":"10.1007\/s10055-005-0153-5"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Arslan, L.M.: Speaker transformation algorithm using segmental codebooks (STASC). Speech Communication (1999)","DOI":"10.1016\/S0167-6393(99)00015-1"},{"key":"1_CR8","unstructured":"Beau, F.: Culture d\u2019Univers - Jeux en r\u00e9seau, mondes virtuels, le nouvel \u00e2ge de la soci\u00e9t\u00e9 num\u00e9rique. Limoges (2007)"},{"key":"1_CR9","volume-title":"Springer Handbook of Speech Processing","year":"2008","unstructured":"Benesty, J., Sondhi, M., Huang, Y. (eds.): Springer Handbook of Speech Processing. Springer, Heidelberg (2008)"},{"key":"1_CR10","unstructured":"Bui, T.D.: Creating Emotions And Facial Expressions For Embodied Agents. PhD thesis, University of Twente, Department of Computer Science, Enschede (2004)"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Cassell, J., Bickmore, J., Billinghurst, M., Campbell, L., Chang, K., Vilhj\u00e1lmsson, H., Yan, H.: Embodiment in conversational interfaces: Rea. In: CHI 1999, Pittsburgh, PA, pp. 520\u2013527 (1999)","DOI":"10.1145\/302979.303150"},{"key":"1_CR12","volume-title":"Trading Spaces: How Humans and Humanoids use Speech and Gesture to Give Directions","author":"J. Cassell","year":"2007","unstructured":"Cassell, J., Kopp, S., Tepper, P., Kim, F.: Trading Spaces: How Humans and Humanoids use Speech and Gesture to Give Directions. John wiley & sons, New york (2007)"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Cassell, J., Vilhj\u00e1lmsson, H., Bickmore, T.: BEAT: the Behavior Expression Animation Toolkit. In: Computer Graphics Proceedings, Annual Conference Series. ACM SIGGRAPH (2001)","DOI":"10.1145\/383259.383315"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Cheyer, A., Martin, D.: The open agent architecture. Journal of Autonomous Agents and Multi-Agent Systems, 143\u2013148 (March 2001)","DOI":"10.1023\/A:1010091302035"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Chi, D., Costa, M., Zhao, L., Badler, N.: The emote model for effort and shape. In: International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH, pp. 173\u2013182 (2000)","DOI":"10.1145\/344779.352172"},{"key":"1_CR16","volume-title":"Progress in Non-Linear Speech Processing","author":"G. Chollet","year":"2007","unstructured":"Chollet, G., Landais, R., Bredin, H., Hueber, T., Mokbel, C., Perrot, P., Zouari, L.: Some experiments in audio-visual speech processing, in non-linear speech processing. In: Chetnaoui, M. (ed.) Progress in Non-Linear Speech Processing. Springer, Heidelberg (2007)"},{"key":"1_CR17","volume-title":"Searching through a speech memory for efficient coding, recognition and synthesis","author":"G. Chollet","year":"2002","unstructured":"Chollet, G., Petrovska-Delacr\u00e9taz, D.: Searching through a speech memory for efficient coding, recognition and synthesis. Franz Steiner Verlag, Stuttgart (2002)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Cootes, T., Edwards, G., Taylor, C.: Active appearance models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 681\u2013685 (2001)","DOI":"10.1109\/34.927467"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Dornaika, F., Ahlberg, J.: Fast and reliable active appearance model search for 3D face tracking. IEEE Transactions on Systems, Man, and Cybernetics, 1838\u20131853 (2004)","DOI":"10.1109\/TSMCB.2004.829135"},{"key":"1_CR20","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1007\/978-3-540-49127-9_21","volume-title":"Springer Handbook of Speech Processing","author":"T. Dutoit","year":"2008","unstructured":"Dutoit, T.: Corpus-based speech synthesis. In: Jacob, B., Mohan, S.M., Yiteng (Arden), H. (eds.) Springer Handbook of Speech Processing, pp. 437\u2013453. Springer, Heidelberg (2008)"},{"key":"1_CR21","volume-title":"Emotions inside out","author":"P. Ekman","year":"2003","unstructured":"Ekman, P., Campos, J., Davidson, R.J., De Waals, F.: Emotions inside out, vol.\u00a01000. Annals of the New York Academy of Sciences, New York (2003)"},{"key":"1_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/11613107_9","volume-title":"Nonlinear Analyses and Algorithms for Speech Processing","author":"A. Esposito","year":"2006","unstructured":"Esposito, A.: Children\u2019s organization of discourse structure through pausing means. In: Faundez-Zanuy, M., Janer, L., Esposito, A., Satue-Villar, A., Roure, J., Espinosa-Duro, V. (eds.) NOLISP 2005. LNCS, vol.\u00a03817, pp. 108\u2013115. Springer, Heidelberg (2006)"},{"key":"1_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/978-3-540-71505-4_13","volume-title":"Progress in Nonlinear Speech Processing","author":"A. Esposito","year":"2007","unstructured":"Esposito, A.: The amount of information on emotional states conveyed by the verbal and nonverbal channels: Some perceptual data. In: Stylianou, Y., Faundez-Zanuy, M., Esposito, A. (eds.) COST 277. LNCS, vol.\u00a04391, pp. 249\u2013268. Springer, Heidelberg (2007)"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Esposito, A., Bourbakis, N.G.: The role of timing in speech perception and speech production processes and its effects on language impaired individuals. In: 6th International IEEE Symposium on BioInformatics and BioEngineering, pp. 348\u2013356 (2006)","DOI":"10.1109\/BIBE.2006.253300"},{"key":"1_CR25","series-title":"NATO Publishing Series","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/978-3-540-76442-7","volume-title":"Fundamentals of Verbal and Nonverbal Communication and the Biometrical Issue","author":"A. Esposito","year":"2007","unstructured":"Esposito, A., Marinaro, M.: What pauses can tell us about speech and gesture partnership. In: Esposito, A., Bratanic, M., Keller, E., Marinaro, M. (eds.) Fundamentals of Verbal and Nonverbal Communication and the Biometrical Issue. NATO Publishing Series, pp. 45\u201357. IOS press, Amsterdam (2007)"},{"key":"1_CR26","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1109\/5.880079","volume":"88","author":"J.L. Gauvain","year":"2000","unstructured":"Gauvain, J.L., Lamel, L.: Large - Vocabulary Continuous Speech Recognition: Advances and Applications. Proceedings of the IEEE\u00a088, 1181\u20131200 (2000)","journal-title":"Proceedings of the IEEE"},{"key":"1_CR27","unstructured":"Genoud, D., Chollet, G.: Voice transformations: Some tools for the imposture of speaker verification systems. In: Braun, A. (ed.) Advances in Phonetics. Franz Steiner Verlag (1999)"},{"key":"1_CR28","unstructured":"Gentes, A.: Second life, une mise en jeu des m\u00e9dias. In: de Cayeux, A., Guibert, C. (eds.) Second life, un monde possible, Les petits matins (2007)"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Gutierrez-Osuna, R., Kakumanu, P., Esposito, A., Garcia, O.N., Bojorquez, A., Castello, J., Rudomin, I.: Speech-driven facial animation with realistic dynamics. In: IEEE Transactions on Multimedia, pp. 33\u201342 (2005)","DOI":"10.1109\/TMM.2004.840611"},{"key":"1_CR30","volume-title":"Guide to Biometric Reference Systems and Performance Evaluation","author":"A. Hannani El","year":"2008","unstructured":"El Hannani, A., Petrovska-Delacr\u00e9taz, D., Fauve, B., Mayoue, A., Mason, J., Bonastre, J.-F., Chollet, G.: Text-independent speaker verification. In: Petrovska-Delacr\u00e9taz, D., Chollet, G., Dorizzi, B. (eds.) Guide to Biometric Reference Systems and Performance Evaluation. Springer, London (2008)"},{"key":"1_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1007\/11678816_22","volume-title":"Gesture in Human-Computer Interaction and Simulation","author":"B. Hartmann","year":"2006","unstructured":"Hartmann, B., Mancini, M., Pelachaud, C.: Implementing expressive gesture synthesis for embodied conversational agents. In: Gibet, S., Courty, N., Kamp, J.-F. (eds.) GW 2005. LNCS (LNAI), vol.\u00a03881, pp. 188\u2013199. Springer, Heidelberg (2006)"},{"key":"1_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/11573548_4","volume-title":"Affective Computing and Intelligent Interaction","author":"D. Heylen","year":"2005","unstructured":"Heylen, D., Ghijsen, M., Nijholt, A., op den Akker, R.: Facial signs of affect during tutoring sessions. In: Tao, J., Tan, T., Picard, R.W. (eds.) ACII 2005. LNCS, vol.\u00a03784, pp. 24\u201331. Springer, Heidelberg (2005)"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Horain, P., Bomb, M.: 3D model based gesture acquisition using a single camera. In: IEEE Workshop on Applications of Computer Vision, pp. 158\u2013162 (2002)","DOI":"10.1109\/ACV.2002.1182175"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Horain, P., Marques-Soares, J., Rai, P.K., Bideau, A.: Virtually enhancing the perception of user actions. In: 15th International Conference on Artificial Reality and Telexistence ICAT 2005, pp. 245\u2013246 (2005)","DOI":"10.1145\/1152399.1152446"},{"key":"1_CR35","unstructured":"IV2: Identification par l\u2019Iris et le Visage via la\u00a0Vid\u00e9o, http:\/\/iv2.ibisc.fr\/pageweb-iv2.html"},{"key":"1_CR36","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/PROC.1976.10159","volume":"64","author":"F. Jelinek","year":"1976","unstructured":"Jelinek, F.: Continuous Speech Recognition by Statistical Methods. Proceedings of the IEEE\u00a064, 532\u2013556 (1976)","journal-title":"Proceedings of the IEEE"},{"key":"1_CR37","unstructured":"Kain, A.: High Resolution Voice Transformation. PhD thesis, Oregon Health and Science University, Portland, USA, october (2001)"},{"key":"1_CR38","unstructured":"Kain, A., Macon, M.: Spectral voice conversion for text to speech synthesis. In: International Conference on Acoustics, Speech, and Signal Processing, New York (1998)"},{"key":"1_CR39","unstructured":"Kain, A., Macon, M.W.: Design and evaluation of a voice conversion algorithm based on spectral envelope mapping and residual prediction. In: International Conference on Acoustics, Speech, and Signal Processing (2001)"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Kakumanu, P., Esposito, A., Gutierrez-Osuna, R., Garcia, O.N.: Comparing different acoustic data-encoding for speech driven facial animation. Speech Communication, 598\u2013615 (2006)","DOI":"10.1016\/j.specom.2005.09.005"},{"issue":"2","key":"1_CR41","first-page":"1","volume":"3","author":"S. Karungaru","year":"2007","unstructured":"Karungaru, S., Fukumi, M., Akamatsu, N.: Automatic human faces morphing using genetic algorithms based control points selection. International Journal of Innovative Computing, Information and Control\u00a03(2), 1\u20136 (2007)","journal-title":"International Journal of Innovative Computing, Information and Control"},{"key":"1_CR42","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511807572","volume-title":"Gesture: Visible action as utterance","author":"A. Kendon","year":"2004","unstructured":"Kendon, A.: Gesture: Visible action as utterance. Cambridge Press, Cambridge (2004)"},{"key":"1_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-540-74997-4_2","volume-title":"Intelligent Virtual Agents","author":"M. Kipp","year":"2007","unstructured":"Kipp, M., Neff, M., Kipp, K.H., Albrecht, I.: Toward natural gesture synthesis: Evaluating gesture units in a data-driven approach. In: Pelachaud, C., Martin, J.-C., Andr\u00e9, E., Chollet, G., Karpouzis, K., Pel\u00e9, D. (eds.) IVA 2007. LNCS (LNAI), vol.\u00a04722, pp. 15\u201328. Springer, Heidelberg (2007)"},{"key":"1_CR44","unstructured":"Kopp, S., Jung, B., Lessmann, N., Wachsmuth, I.: Max - a multimodal assistant in virtual reality construction. KI Kunstliche Intelligenz (2003)"},{"issue":"1","key":"1_CR45","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1002\/cav.6","volume":"15","author":"S. Kopp","year":"2004","unstructured":"Kopp, S., Wachsmuth, I.: Synthesizing multimodal utterances for conversational agents. The Journal Computer Animation and Virtual Worlds\u00a015(1), 39\u201352 (2004)","journal-title":"The Journal Computer Animation and Virtual Worlds"},{"key":"1_CR46","volume-title":"Webster dictionary","author":"C. Laird","year":"1996","unstructured":"Laird, C.: Webster\u2019s New\u00a0World Dictionary, and Thesaurus. In: Webster dictionary. Macmillan, Basingstoke (1996)"},{"key":"1_CR47","unstructured":"Li, Y., Wen, Y.: A study on face morphing algorithms, http:\/\/scien.stanford.edu\/class\/ee368\/projects2000\/project17"},{"key":"1_CR48","series-title":"Approaches to semiotics","doi-asserted-by":"crossref","DOI":"10.1515\/9783112418260","volume-title":"American Sign Language Syntax","author":"S. Lidell","year":"1980","unstructured":"Lidell, S.: American Sign Language Syntax. Approaches to semiotics. Mouton, The Hague (1980)"},{"key":"1_CR49","unstructured":"Lu, S., Huang, G., Samaras, D., Metaxas, D.: Model-based integration of visual cues for hand tracking. In: IEEE workshop on Motion and Video Computing (2002)"},{"key":"1_CR50","unstructured":"Mancini, M., Pelachaud, C.: Distinctiveness in multimodal behaviors. In: Seventh International Joint Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2008, Estoril Portugal (May 2008)"},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Matthews, I., Baker, S.: Active appearance models revisited. International Journal of Computer Vision, 135\u2013164 (2004)","DOI":"10.1023\/B:VISI.0000029666.37597.d3"},{"key":"1_CR52","doi-asserted-by":"crossref","unstructured":"McNeill, D.: Gesture and though. University of Chicago Press (2005)","DOI":"10.7208\/chicago\/9780226514642.001.0001"},{"key":"1_CR53","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.cviu.2006.08.002","volume":"4","author":"T. Moeslund","year":"2006","unstructured":"Moeslund, T., Hilton, A., Kruger, V.: A survey of advances in vision-based human motion capture and analysis. Computer vision and image understanding\u00a04, 90\u2013126 (2006)","journal-title":"Computer vision and image understanding"},{"key":"1_CR54","unstructured":"Moon, K., Pavlovic, V.I.: Impact of dynamics on subspace embedding and tracking of sequences. In: Conference on Computer Vision and Pattern Recognition, New York, pp. 198\u2013205 (2006)"},{"key":"1_CR55","doi-asserted-by":"crossref","unstructured":"Niewiadomski, R., Pelachaud, C.: Model of facial expressions management for an embodied conversational agent. In: 2nd International Conference on Affective Computing and Intelligent Interaction ACII, Lisbon (September 2007)","DOI":"10.1007\/978-3-540-74889-2_2"},{"key":"1_CR56","doi-asserted-by":"crossref","unstructured":"Ochs, M., Niewiadomski, R., Pelachaud, C., Sadek, D.: Intelligent expressions of emotions. In: 1st International Conference on Affective Computing and Intelligent Interaction ACII, China (October 2005)","DOI":"10.1007\/11573548_91"},{"key":"1_CR57","doi-asserted-by":"crossref","unstructured":"Padmanabhan, M., Picheny, M.: Large Vocabulary Speech Recognition Algorithms. Computer Magazine\u00a035 (2002)","DOI":"10.1109\/2.993770"},{"key":"1_CR58","volume-title":"MPEG4 Facial Animation - The standard, implementations and applications","year":"2002","unstructured":"Pandzic, I.S., Forcheimer, R. (eds.): MPEG4 Facial Animation - The standard, implementations and applications. John Wiley & Sons, Chichester (2002)"},{"key":"1_CR59","doi-asserted-by":"crossref","unstructured":"Park, I.K., Zhang, H., Vezhnevets, V.: Image based 3D face modelling system. EURASIP Journal on Applied Signal Processing, 2072\u20132090 (January 2005)","DOI":"10.1155\/ASP.2005.2072"},{"key":"1_CR60","doi-asserted-by":"crossref","unstructured":"Pelachaud, C., Martin, J.-C., Andr\u00e9, E., Chollet, G., Karpouzis, K., Pel\u00e9, D.: Intelligent virtual agents. In: 7th International Working Conference, IVA 2007 (2007)","DOI":"10.1007\/978-3-540-74997-4"},{"key":"1_CR61","volume-title":"Progress in Non-Linear Speech Processing","author":"P. Perrot","year":"2007","unstructured":"Perrot, P., Aversano, G., Chollet, G.: Voice disguise and automatic detection, review and program. In: Stylianou, Y. (ed.) Progress in Non-Linear Speech Processing. Springer, Heidelberg (2007)"},{"key":"1_CR62","doi-asserted-by":"crossref","unstructured":"Perrot, P., Aversano, G., Blouet, G.R., Charbit, M., Chollet, G.: Voice forgery using alisp: Indexation in a client memory. In: International Conference on Acoustics, Speech, and Signal Processing, Philadelphia, pp. 17\u201320 (2005)","DOI":"10.1109\/ICASSP.2005.1415039"},{"key":"1_CR63","volume-title":"Progress in Non-Linear Speech Processing","author":"D. Petrovska-Delacr\u00e9taz","year":"2007","unstructured":"Petrovska-Delacr\u00e9taz, D., El Hannani, A., Chollet, G.: Automatic speaker verification, state of the art and current issues. In: Stylianou, Y. (ed.) Progress in Non-Linear Speech Processing. Springer, Heidelberg (2007)"},{"key":"1_CR64","unstructured":"Petrovska-Delacr\u00e9taz, D., Lelandais, S., Colineau, J., Chen, L., Dorizzi, B., Krichen, E., Mellakh, M.A., Chaari, A., Guerfi, S., D\u2019Hose, J., Ardabilian, M., Ben Amor, B.: The iv2 multimodal (2D, 3D, stereoscopic face, talking face and iris) biometric database, and the iv2 2007 evaluation campaign. In: The proceedings of the IEEE Second International Conference on Biometrics: Theory, Applications (BTAS), Washington DC, USA (September 2008)"},{"key":"1_CR65","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.cviu.2006.10.016","volume":"108","author":"R. Poppe","year":"2007","unstructured":"Poppe, R.: Vision-based human motion analysis: an overview. Computer vision and image understanding\u00a0108, 4\u201318 (2007)","journal-title":"Computer vision and image understanding"},{"key":"1_CR66","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/0-387-27257-7_11","volume-title":"Handbook of Face Recognition","author":"S. Romdhani","year":"2005","unstructured":"Romdhani, S., Blanz, V., Basso, C., Vetter, T.: Morphable models of faces. In: Li, S., Jain, A. (eds.) Handbook of Face Recognition, pp. 217\u2013245. Springer, Heidelberg (2005)"},{"key":"1_CR67","doi-asserted-by":"crossref","unstructured":"Ruttkay, Z., Noot, H., ten Hagen, P.: Emotion disc and emotion squares: tools to explore the facial expression space. Computer Graphics Forum, 49\u201353 (2003)","DOI":"10.1111\/1467-8659.t01-1-00645"},{"key":"1_CR68","doi-asserted-by":"crossref","unstructured":"Sminchisescu, C.: 3D Human Motion Analysis in Monocular Video, Techniques and Challenges. In: AVSS 2006: Proceedings of the IEEE International Conference on Video and Signal Based Surveillance, p. 76 (2006)","DOI":"10.1109\/AVSS.2006.3"},{"key":"1_CR69","doi-asserted-by":"crossref","unstructured":"Sminchisescu, C., Triggs, B.: Estimating articulated human motion with covariance scaled sampling. International Journal of Robotic Research, 371\u2013392 (2003)","DOI":"10.1177\/0278364903022006003"},{"key":"1_CR70","unstructured":"Marques Soares, J., Horain, P., Bideau, A., Nguyen, M.H.: Acquisition 3D du geste par vision monoscopique en temps r\u00e9el et t\u00e9l\u00e9pr\u00e9sence. In: Acquisition du geste humain par vision artificielle et applications, pp. 23\u201327 (2004)"},{"key":"1_CR71","doi-asserted-by":"crossref","unstructured":"S\u00fcndermann, D., Ney, H.: VTLN-Based Cross-Language Voice Conversion. In: IEEE workshop on Automatic Speech Recognition and Understanding, Virgin Islands, pp. 676\u2013681 (2003)","DOI":"10.1109\/ASRU.2003.1318521"},{"key":"1_CR72","doi-asserted-by":"crossref","unstructured":"Terzopoulos, D., Waters, K.: Analysis and synthesis of facial image sequences using physical and anatomical models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 569\u2013579 (1993)","DOI":"10.1109\/34.216726"},{"key":"1_CR73","unstructured":"Thiebaux, M., Marshall, A., Marsella, S., Kallmann, M.: SmartBody: Behavior realization for embodied conversational agents. In: Seventh International Joint Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2008, Portugal (May 2008)"},{"key":"1_CR74","unstructured":"Thorisson, K.R., List, T., Pennock, C., DiPirro, J.: Whiteboards: Scheduling blackboards for semantic routing of messages and streams. In: AAAI 2005 Workshop on Modular Construction of Human-Like Intelligence, July 10 (2005)"},{"key":"1_CR75","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1007\/978-3-540-79037-2_16","volume-title":"Modeling Communication with Robots and Virtual Humans","author":"D. Traum","year":"2008","unstructured":"Traum, D.: Talking to virtual humans: Dialogue models and methodologies for embodied conversational agents. In: Wachsmuth, I., Knoblich, G. (eds.) Modeling Communication with Robots and Virtual Humans, pp. 296\u2013309. John Wiley & Sons, Chichester (2008)"},{"key":"1_CR76","volume-title":"MPEG4 Facial Animation - The standard, implementations and applications","author":"N. Tsapatsoulis","year":"2002","unstructured":"Tsapatsoulis, N., Raouzaiou, A., Kollias, S., Cowie, R., Douglas-Cowie, E.: Emotion recognition and synthesis based on MPEG-4 FAPs in MPEG-4 facial animation. In: Pandzic, I.S., Forcheimer, R. (eds.) MPEG4 Facial Animation - The standard, implementations and applications. John Wiley & Sons, Chichester (2002)"},{"key":"1_CR77","unstructured":"Turajlic, E., Rentzos, D., Vaseghi, S., Ho, C.-H.: Evaluation of methods for parametric formant transformation in voice conversion. In: International Conference on Acoustics, Speech, and Signal Processing (2003)"},{"key":"1_CR78","volume-title":"Life on the screen, Identity in the age of the internet","author":"S. Turkle","year":"1997","unstructured":"Turkle, S.: Life on the screen, Identity in the age of the internet. Simon and Schuster, New York (1997)"},{"key":"1_CR79","doi-asserted-by":"crossref","unstructured":"Urtasun, R., Fleet, D.J., Fua, P.: 3D people tracking with gaussian process dynamical models. In: Conference on Computer Vision and Pattern Recognition, New York, pp. 238\u2013245 (2006)","DOI":"10.1109\/CVPR.2006.15"},{"key":"1_CR80","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/978-3-540-74997-4_10","volume-title":"Intelligent Virtual Agents","author":"H. Vilhjalmsson","year":"2007","unstructured":"Vilhjalmsson, H., Cantelmo, N., Cassell, J., Chafai, N.E., Kipp, M., Kopp, S., Mancini, M., Marsella, S., Marshall, A.N., Pelachaud, C., Ruttkay, Z., Th\u00f3risson, K.R., van Welbergen, H., van der Werf, R.: The behavior markup language: Recent developments and challenges. In: Pelachaud, C., Martin, J.-C., Andr\u00e9, E., Chollet, G., Karpouzis, K., Pel\u00e9, D. (eds.) IVA 2007. LNCS, vol.\u00a04722, pp. 99\u2013111. Springer, Heidelberg (2007)"},{"key":"1_CR81","doi-asserted-by":"crossref","unstructured":"Wiskott, L., Fellous, J.M., Kr\u00fcger, N., von der Malsburg, C.: Analysis and synthesis of facial image sequences using physical and anatomical models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 775\u2013779 (1997)","DOI":"10.1109\/34.598235"},{"key":"1_CR82","doi-asserted-by":"crossref","unstructured":"Wolberg, G.: Recent advances in image morphing. Computer Graphics Internat, 64\u201371 (1996)","DOI":"10.1109\/CGI.1996.511788"},{"key":"1_CR83","unstructured":"Xiao, J., Baker, S., Matthews, I., Kanade, T.: Real-time combined 2D+3D active appearance models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 25\u201335 (2004)"},{"key":"1_CR84","doi-asserted-by":"crossref","unstructured":"Ye, H., Young, S.: Perceptually weighted linear transformation for voice conversion. In: Eurospeech (2003)","DOI":"10.21437\/Eurospeech.2003-663"},{"key":"1_CR85","unstructured":"Yegnanarayana, B., Sharat Reddy, K., Kishore, S.P.: Source and system features for speaker recognition using AANN models. In: International Conference on Acoustics, Speech, and Signal Processing (2001)"},{"key":"1_CR86","unstructured":"Young, S.: Statistical Modelling in Continuous Speech Recognition. In: Proceedings of the 17th International Conference on Uncertainty in Artificial Intelligence, Seattle, WA (August 2001)"},{"key":"1_CR87","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1007\/978-3-540-24694-7_70","volume-title":"MICAI 2004: Advances in Artificial Intelligence","author":"V. Zanella","year":"2004","unstructured":"Zanella, V., Fuentes, O.: An Approach to Automatic Morphing of Face Images in Frontal View. In: Monroy, R., Arroyo-Figueroa, G., Sucar, L.E., Sossa, H. (eds.) MICAI 2004. LNCS, vol.\u00a02972, pp. 679\u2013687. Springer, Heidelberg (2004)"}],"container-title":["Lecture Notes in Computer Science","Multimodal Signals: Cognitive and Algorithmic Issues"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-00525-1_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T18:59:22Z","timestamp":1738954762000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-00525-1_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642005244","9783642005251"],"references-count":87,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-00525-1_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009]]}}}