{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:49Z","timestamp":1740122869274,"version":"3.37.3"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2016,3,3]],"date-time":"2016-03-03T00:00:00Z","timestamp":1456963200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"National High-Tech Research and Development Program of China(863 Program)","award":["2015AA016305"],"award-info":[{"award-number":["2015AA016305"]}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China (NSFC)","doi-asserted-by":"crossref","award":["61273288"],"award-info":[{"award-number":["61273288"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China (NSFC)","doi-asserted-by":"crossref","award":["61233009"],"award-info":[{"award-number":["61233009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China (NSFC)","doi-asserted-by":"crossref","award":["61203258"],"award-info":[{"award-number":["61203258"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China (NSFC)","doi-asserted-by":"crossref","award":["61375027"],"award-info":[{"award-number":["61375027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China (NSFC)","doi-asserted-by":"crossref","award":["61332017"],"award-info":[{"award-number":["61332017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China (NSFC)","doi-asserted-by":"crossref","award":["61425017"],"award-info":[{"award-number":["61425017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2016,5]]},"DOI":"10.1007\/s11042-016-3405-3","type":"journal-article","created":{"date-parts":[[2016,3,3]],"date-time":"2016-03-03T02:45:33Z","timestamp":1456973133000},"page":"5125-5146","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Emotional head motion predicting from prosodic and linguistic features"],"prefix":"10.1007","volume":"75","author":[{"given":"Minghao","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinlin","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaihui","family":"Mu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,3,3]]},"reference":[{"unstructured":"Alberto B, Piero C, Giuseppe RL, Giulio P (2014) LuciaWebGL a new WebGL-based talking head, 15th Annual Conference of the International Speech Communication Association, Singapore (InterSpeech 2014 Show & Tell Contribution)","key":"3405_CR1"},{"unstructured":"Aleksandra C, Tomislav P, Pandzic IS (2009) RealActor: character animation and multimodal behavior realization system. IVA: 486\u2013487","key":"3405_CR2"},{"issue":"1","key":"3405_CR3","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1109\/TASL.2007.907570","volume":"16","author":"S Ananthakrishnan","year":"2008","unstructured":"Ananthakrishnan S, Narayanan S (2008) Automatic prosodic event detection using acoustic, lexical, and syntactic evidence. IEEE Trans Audio Speech Lang Process 16(1):216\u2013228","journal-title":"IEEE Trans Audio Speech Lang Process"},{"unstructured":"Badler N, Steedman M, Achorn B, Bechet T, Douville B, Prevost S, Cassell J, Pelachaud C, Stone M (1994) Animated conversation: rule-based generation of facial expression gesture and spoken intonation for multiple conversation agents. Proceedings of SIGGRAPH, 73\u201380","key":"3405_CR4"},{"doi-asserted-by":"crossref","unstructured":"Ben-Youssef A, Shimodaira H, Braude DA (2014) Speech driven talking head from estimated articulatory features, The 40th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2014), Florence, Italy","key":"3405_CR5","DOI":"10.1109\/ICASSP.2014.6854468"},{"unstructured":"Bevacqua E, Hyniewska SJ, Pelachaud C (2010) Evaluation of a virtual listener smiling behavior. Proceedings of the 23rd International Conference on Computer Animation and Social Agents, Saint-Malo, France","key":"3405_CR6"},{"unstructured":"Bo X, Georgiou Panayiotis G, Brian Baucom, Shrikanth S (2014) Narayanan, power-spectral analysis of head motion signal for behavioral modeling in human interaction, 2014 I.E. International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2014), Florence, Italy","key":"3405_CR7"},{"doi-asserted-by":"crossref","unstructured":"Bodenheimer B, Rose C, Rosenthal S, Pella J (1997) The process of motion capture: dealing with the data. In: Thalmann (ed) Computer animation and simulation. Springer NY 318 Eurographics Animation Workshop","key":"3405_CR8","DOI":"10.1007\/978-3-7091-6874-5_1"},{"doi-asserted-by":"crossref","unstructured":"Boulic R, Becheiraz P, Emering L, Thalmann D (1997) Integration of motion control techniques for virtual human and avatar real-time animation. In: Proc. of Virtual Reality Software and Technology, Switzerland: 111\u2013118","key":"3405_CR9","DOI":"10.1145\/261135.261156"},{"issue":"3\u20134","key":"3405_CR10","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1002\/cav.80","volume":"16","author":"C Busso","year":"2005","unstructured":"Busso C, Deng Z, Neumann U, Narayanan S (2005) Natural head motion synthesis driven by acoustic prosodic features. Comput Anim Virtual Worlds 16(3\u20134):283\u2013290","journal-title":"Comput Anim Virtual Worlds"},{"doi-asserted-by":"crossref","unstructured":"Cassell J, Vilhjalmsson HH, Bickmore TW (2001) Beat: the behavior expression animation toolkit. In: Proceedings of SIGGRAPH, 477\u2013486","key":"3405_CR11","DOI":"10.1145\/383259.383315"},{"unstructured":"Chuang D, Pengcheng Z, Lei X, Dongmei J, ZhongHua Fu (2014) Northwestern, speech-driven head motion synthesis using neural networks, 15th Annual Conference of the International Speech Communication Association, Singapore (InterSpeech 2014)","key":"3405_CR12"},{"key":"3405_CR13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1142\/S0219691304000317","volume":"2","author":"JF Cohn","year":"2004","unstructured":"Cohn JF, Schmidt KL (2004) The timing of facial motion in posed and spontaneous smiles. Int J Wavelets Multiresolution Inf Process 2:1\u201312","journal-title":"Int J Wavelets Multiresolution Inf Process"},{"doi-asserted-by":"crossref","unstructured":"Cowie R, Douglas-Cowie E (2001) Emotion recognition in human-computer interaction. IEEE Signal Processing Magazine. pp. 33\u201380","key":"3405_CR14","DOI":"10.1109\/79.911197"},{"issue":"1\u20132","key":"3405_CR15","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/S1071-5819(03)00020-X","volume":"59","author":"F Rosis de","year":"2003","unstructured":"de Rosis F, Pelachaud C, Poggi I, Carofiglio V, De Carolis N (2003) From Greta\u2019s mind to her face: modeling the dynamics of affective states in a conversational embodied agent, special issue on applications of affective computing in human-computer interaction. Int J Hum Comput Stud 59(1\u20132):81\u2013118","journal-title":"Int J Hum Comput Stud"},{"doi-asserted-by":"crossref","unstructured":"Faloutsos P, van de Panne M, Terzopoulos D (2001) Composable controllers for physics-based character animation. In: SIGGRAPH \u201801: proceedings of the 28th annual conference on Computer graphics and interactive techniques. ACM Press, New York, p 251\u2013260","key":"3405_CR16","DOI":"10.1145\/383259.383287"},{"unstructured":"Fangzhou L, Huibin J, Jianhua T (2008) A maximum entropy based hierarchical model for automatic prosodic boundary labeling in Mandarin. In: Proceedings of 6th International Symposium on Chinese Spoken Language Processing","key":"3405_CR17"},{"doi-asserted-by":"crossref","unstructured":"Graf HP, Cosatto E, Strom V, Huang F (2002) Visual prosody: facial movements accompanying speech. In: Fifth IEEE International Conference on Automatic Face and Gesture Recognition. Washinton D.C., USA","key":"3405_CR18","DOI":"10.1109\/AFGR.2002.1004186"},{"key":"3405_CR19","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1109\/TNN.2002.1021892","volume":"13","author":"P Hong","year":"2002","unstructured":"Hong P, Wen Z, Huang TS (2002) Real-time speech-driven face animation with expressions using neural networks. IEEE Trans Neural Netw 13:916\u2013927","journal-title":"IEEE Trans Neural Netw"},{"unstructured":"Huibin J, Jianhua T, Wang X (2008) Prosody variation: application to automatic prosody evaluation of mandarin speech. In: Speech prosody, Brail","key":"3405_CR20"},{"issue":"3","key":"3405_CR21","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1109\/TASL.2010.2052246","volume":"19","author":"J Jia","year":"2011","unstructured":"Jia J, Shen Z, Fanbo M, Yongxin W, Lianhong C (2011) Emotional audio-visual speech synthesis based on PAD. IEEE Trans Audio Speech Lang Process 19(3):570\u2013582","journal-title":"IEEE Trans Audio Speech Lang Process"},{"doi-asserted-by":"crossref","unstructured":"Jianwu D, Kiyoshi H (Feb 2004) Construction and control of a physiological articulatory model. J Acoust Soc Am 115(2):853\u2013870","key":"3405_CR22","DOI":"10.1121\/1.1639325"},{"doi-asserted-by":"crossref","unstructured":"Kipp M, Heloir A, Gebhard P, Schroeder M (2010) Realizing multimodal behavior: closing the gap between behavior planning and embodied agent presentation. In: Proceedings of the 10th International Conference on Intelligent Virtual Agents. Springer","key":"3405_CR23","DOI":"10.1007\/978-3-642-15892-6_7"},{"unstructured":"Kopp S, Jung B, Lebmann N, Wachsmuth (2003) I: Max - a multimodal assistant in virtual reality construction. KI -Kunstliche Intelligenz 4\/03 117","key":"3405_CR24"},{"issue":"1","key":"3405_CR25","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1002\/cav.6","volume":"15","author":"S Kopp","year":"2004","unstructured":"Kopp S, Wachsmuth I (2004) Synthesizing multimodal utterances for conversational agents. Comput Anim Virtual Worlds 15(1):39\u201352","journal-title":"Comput Anim Virtual Worlds"},{"issue":"10","key":"3405_CR26","first-page":"2325","volume":"40","author":"X Lei","year":"2007","unstructured":"Lei X, Zhiqiang L (2007) A coupled HMM approach for video-realistic speech animation. Pattern Recogn 40(10):2325\u20132340","journal-title":"Pattern Recogn"},{"issue":"3","key":"3405_CR27","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/TMM.2006.888009","volume":"9","author":"X Lei","year":"2007","unstructured":"Lei X, Zhiqiang L (2007) Realistic mouth-synching for speech-driven talking face using articulatory modelling. IEEE Trans Multimedia 9(3):500\u2013510","journal-title":"IEEE Trans Multimedia"},{"unstructured":"Lijuan W, Xiaojun Q, Wei H, Frank KS (2010) Synthesizing photo-real talking head via trajectory-guided sample selection. INTERSPEECH 2010","key":"3405_CR28"},{"doi-asserted-by":"crossref","unstructured":"Martin JC, Niewiadomski R, Devillers L, Buisine S, Pelachaud C (2006) Multimodal complex emotions: gesture expressivity and blended facial expressions. International Journal of Humanoid Robotics, special issue Achieving Human-Like Qualities in Interactive Virtual and Physical Humanoids, 3(3): 269\u2013292","key":"3405_CR29","DOI":"10.1142\/S0219843606000825"},{"issue":"z1","key":"3405_CR30","first-page":"420","volume":"20","author":"Z Meng","year":"2008","unstructured":"Meng Z, Kaihui M, Jianhua T (2008) An expressive TTVS system based on dynamic unit selection. J Syst Simul 20(z1):420\u2013422","journal-title":"J Syst Simul"},{"doi-asserted-by":"crossref","unstructured":"Parke F (1972) Computer generated animation of faces. Proceedings of the ACM National Conference","key":"3405_CR31","DOI":"10.1145\/800193.569955"},{"key":"3405_CR32","doi-asserted-by":"crossref","first-page":"3539","DOI":"10.1098\/rstb.2009.0186","volume":"364","author":"Pelachaud","year":"2009","unstructured":"Pelachaud (2009) Modelling multimodal expression of emotion in a virtual agent. Philos Trans R Soc B Biol Sci 364:3539\u20133548","journal-title":"Philos Trans R Soc B Biol Sci"},{"issue":"3","key":"3405_CR33","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1109\/TVCG.2005.43","volume":"11","author":"AK Scott","year":"2005","unstructured":"Scott AK, Parent RE (2005) Creating speech-synchronized animation. IEEE Trans Vis Comput Graph 11(3):341\u2013352","journal-title":"IEEE Trans Vis Comput Graph"},{"issue":"1","key":"3405_CR34","first-page":"49","volume":"26","author":"Y Shao","year":"2007","unstructured":"Shao Y, Han J, Zhao Y, Liu T (2007) Study on automatic prediction of sentential stress for Chinese Putonghua Text-to-Speech system with natural style. Chin J Acoust 26(1):49\u201392","journal-title":"Chin J Acoust"},{"key":"3405_CR35","first-page":"58","volume":"6","author":"Y Shiwen","year":"2000","unstructured":"Shiwen Y, Xuefeng Z, Huiming D (2000) The guideline for segmentation and part-of-speech tagging on very large scale corpus of contemporary Chinese. J Chin Inf Process 6:58\u201364","journal-title":"J Chin Inf Process"},{"unstructured":"Shiwen Y, Xuefeng Z, Huiming D (2002) The basic processing of contemporary Chinese corpus at Peking University SPECIFICATION 16(6)","key":"3405_CR36"},{"doi-asserted-by":"crossref","unstructured":"Song M, Bu J, Chen C, Li N (2004) Audio-visual based emotion recognition- a new approach. In: Proc. of the 2004 I.E. Computer Society Conference on Computer Vision and Pattern Recognition. pp.1020\u20131025","key":"3405_CR37","DOI":"10.1109\/CVPR.2004.1315276"},{"doi-asserted-by":"crossref","unstructured":"Stone M, DeCarlo D, Oh I, Rodriguez C, Stere A, Lees A, Bregler C (2004) Speaking with hands: creating animated conversational characters from recordings of human perfor- mance. ACM Trans Graph (SIGGRAPH\u201804) 23(3):506\u201351","key":"3405_CR38","DOI":"10.1145\/1015706.1015753"},{"key":"3405_CR39","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1023\/A:1008166717597","volume":"38","author":"E Tony","year":"2000","unstructured":"Tony E, Poggio T (2000) Visual speech synthesis by morphing visemes. Int J Comput Vis 38:45\u201357","journal-title":"Int J Comput Vis"},{"key":"3405_CR40","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/978-3-540-79037-2_15","volume-title":"Modeling communication with robots and virtual humans","author":"Wachsmuth","year":"2008","unstructured":"Wachsmuth (2008) \u2018I, Max\u2019 - communicating with an artificial agent. In: Wachsmuth I, Knoblich G (eds) Modeling communication with robots and virtual humans. Springer, Berlin, pp 279\u2013295"},{"doi-asserted-by":"crossref","unstructured":"Wang QR, Suen CY (1984) Analysis and design of a decision tree based on entropy reduction and its application to large character set recognition. IEEE Trans Pattern Anal Mach Intell, PAMI 6: 406\u2013417","key":"3405_CR41","DOI":"10.1109\/TPAMI.1984.4767546"},{"unstructured":"Waters K (1987) A musele model for animating three dimensional facial ExPression. Computer Graphics (SIGGRAPH,87) 22(4): 7\u201324","key":"3405_CR42"},{"issue":"7","key":"3405_CR43","first-page":"1399","volume":"14","author":"Z Wei","year":"2009","unstructured":"Wei Z, Zengfu W (2009) Speech rate related facial animation synthesis and evaluation. J Image Graph 14(7):1399\u20131405","journal-title":"J Image Graph"},{"issue":"4","key":"3405_CR44","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1007\/s12193-010-0051-3","volume":"3","author":"HV Welbergen","year":"2010","unstructured":"Welbergen HV, Reidsma D, Ruttkay ZM, Zwiers EJ (2010) A BML realizer for continuous, multimodal interaction with a virtual human. J Multimodal User Interf 3(4):271\u2013284, ISSN 1783\u20137677","journal-title":"J Multimodal User Interf"},{"issue":"1\u20132","key":"3405_CR45","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/S0167-6393(98)00054-5","volume":"26","author":"E Yamamoto","year":"1998","unstructured":"Yamamoto E, Nakamura S, Shikano K (1998) Lip movement synthesis from speech based on Hidden Markov Models. Speech Comm 26(1\u20132):105\u2013115","journal-title":"Speech Comm"},{"unstructured":"Yamamoto SNE, Shikano K (1997) Speech to lip movement synthesis by HMM. In: Proc.AVSP\u201897. Rhodes, Greece","key":"3405_CR46"},{"unstructured":"Young S, Evermann G, Kershaw D, Moore G, Odell J, Ollason D, Povey D, Valtchev V, Woodland P (2002) The HTK book (for HTK version 3.2). Cambridge University Engineering Department","key":"3405_CR47"},{"unstructured":"Young S, Jansen J, Odell J, Ollason D, Woodland P (1990) The HTK book. Entropic Labs and Cambridge University, 2.1","key":"3405_CR48"},{"issue":"1","key":"3405_CR49","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/TPAMI.2008.52","volume":"31","author":"Z Zeng","year":"2009","unstructured":"Zeng Z, Pantic M, Roisman GI, Huang TS (2009) A survey of affect recognition methods: audio, visual, and spontaneous expressions. IEEE Trans Pattern Anal Mach Intell 31(1):39\u201358","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"3405_CR50","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1109\/TMM.2006.886310","volume":"9","author":"Z Zeng","year":"2007","unstructured":"Zeng Z, Tu J, Liu M, Huang TS, Pianfetti B, Roth D, Levinson S (2007) Audiovisual affect recognition. IEEE Trans Multimedia 9(2):424\u2013428","journal-title":"IEEE Trans Multimedia"},{"doi-asserted-by":"crossref","unstructured":"Zhang S, Wu Z, Meng MLH, Cai L (2007) Head movement synthesis based on semantic and prosodic features for a Chinese expressive avatar. In: IEEE Conference on International Conference on Acoustics, Speech and Signal Processing","key":"3405_CR51","DOI":"10.1109\/ICASSP.2007.367043"},{"issue":"10","key":"3405_CR52","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1016\/j.specom.2010.06.006","volume":"52","author":"L Zhenhua","year":"2010","unstructured":"Zhenhua L, Richmond K, Yamagishi J (2010) An analysis of HMM-based prediction of articulatory movements. Speech Comm 52(10):834\u2013846","journal-title":"Speech Comm"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-016-3405-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-016-3405-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-016-3405-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,5]],"date-time":"2019-09-05T01:59:01Z","timestamp":1567648741000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-016-3405-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3,3]]},"references-count":52,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2016,5]]}},"alternative-id":["3405"],"URL":"https:\/\/doi.org\/10.1007\/s11042-016-3405-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2016,3,3]]}}}