{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T09:40:17Z","timestamp":1782985217432,"version":"3.54.5"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2009,8,20]],"date-time":"2009-08-20T00:00:00Z","timestamp":1250726400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2010,8]]},"DOI":"10.1007\/s11042-009-0344-2","type":"journal-article","created":{"date-parts":[[2009,8,19]],"date-time":"2009-08-19T09:00:19Z","timestamp":1250672419000},"page":"277-297","source":"Crossref","is-referenced-by-count":131,"title":["Multimodal information fusion application to human emotion recognition from face and speech"],"prefix":"10.1007","volume":"49","author":[{"given":"Muharram","family":"Mansoorizadeh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nasrollah","family":"Moghaddam Charkari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2009,8,20]]},"reference":[{"issue":"11","key":"344_CR1","doi-asserted-by":"crossref","first-page":"2049","DOI":"10.1037\/0022-3514.37.11.2049","volume":"37","author":"JN Bassili","year":"1979","unstructured":"Bassili JN (1979) Emotion recognition: the role of facial movement and the relative importance of upper and lower areas of the face. J Pers Soc Psychol 37(11):2049\u20132058","journal-title":"J Pers Soc Psychol"},{"key":"344_CR2","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1023\/A:1007977618277","volume":"25","author":"MJ Black","year":"1997","unstructured":"Black MJ, Yacoob Y (1997) Recognizing facial expressions in image sequences using local parameterized models of image motion. Int J Comput Vis 25:23\u201348","journal-title":"Int J Comput Vis"},{"key":"344_CR3","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/j.ijhcs.2006.11.016","volume":"65","author":"K Boehner","year":"2007","unstructured":"Boehner K, DePaula R, Dourish P, Sengers P (2007) How emotion is made and measured. Int J Human Comput Stud 65:275\u2013291","journal-title":"Int J Human Comput Stud"},{"key":"344_CR4","unstructured":"Boersma P, Weenink D (2007) Praat: doing phonetics by computer (version 4.6.12) [computer program]"},{"key":"344_CR5","doi-asserted-by":"crossref","first-page":"2331","DOI":"10.1109\/TASL.2007.905145","volume":"15","author":"C Busso","year":"2007","unstructured":"Busso C, Narayanan SS (2007) Interrelation between speech and facial gestures in emotional utterances: a single subject study. IEEE Trans Audio Speech Lang Process 15:2331\u20132347","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"344_CR6","volume-title":"Affect and emotion in human-computer interaction, vol 4868","author":"G Castellano","year":"2008","unstructured":"Castellano G, Kessous L, Caridakis G (2008) Emotion recognition through multiple modalities: face, body gesture, speech. In: Beale R (ed) Affect and emotion in human-computer interaction, vol 4868. Springer, New York"},{"key":"344_CR7","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/79.911197","volume":"18","author":"R Cowie","year":"2001","unstructured":"Cowie R, Douglas-Cowie E, Tsapatsoulis N, Votsis G, Kollias S, Fellenz W, Taylor JG (2001) Emotion recognition in human-computer interaction. Signal Process Mag IEEE 18:32\u201380","journal-title":"Signal Process Mag IEEE"},{"key":"344_CR8","doi-asserted-by":"crossref","unstructured":"De Silva LC, Pei Chi N (2000) Bimodal emotion recognition. In: Proceedings of the fourth IEEE international conference on automatic face and gesture recognition, vol 1, pp 332\u2013335","DOI":"10.1109\/AFGR.2000.840655"},{"issue":"3","key":"344_CR9","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/6046.865479","volume":"2","author":"S Dupont","year":"2000","unstructured":"Dupont S, Luettin J (2000) Audio-visual speech modeling for continuous speech recognition. IEEE Trans Multimedia 2(3):141\u2013151","journal-title":"IEEE Trans Multimedia"},{"key":"344_CR10","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1037\/0003-066X.48.4.384","volume":"48","author":"P Ekman","year":"1993","unstructured":"Ekman P (1993) Facial expression and emotion. Am Psychol 48:384\u2013392","journal-title":"Am Psychol"},{"key":"344_CR11","unstructured":"Ekman P, Friesen WV, Hager JC (2002) Facial Action Coding System (FACS), the manual: a human face"},{"key":"344_CR12","doi-asserted-by":"crossref","unstructured":"Fasel B, Luettin J (1999) Automatic facial expression analysis: a survey, vol 36","DOI":"10.1016\/S0031-3203(02)00052-3"},{"key":"344_CR13","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1016\/j.neunet.2005.03.006","volume":"18","author":"N Fragopanagos","year":"2005","unstructured":"Fragopanagos N, Taylor JG (2005) Emotion recognition in human-computer interaction. Neural Netw 18:389\u2013405","journal-title":"Neural Netw"},{"key":"344_CR14","first-page":"185","volume-title":"Affective computing: focus on emotion expression","author":"H Gunes","year":"2008","unstructured":"Gunes H, Piccardi M, Pantic M (2008) From the lab to the real world: affect recognition using multiple cues and modalities. In: Or J (ed) Affective computing: focus on emotion expression. InTech Education and Publishing, Vienna, pp 185\u2013218"},{"key":"344_CR15","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.1109\/34.722606","volume":"20","author":"GD Hager","year":"1998","unstructured":"Hager GD, Belhumeur PN (1998) Efficient region tracking with parametric models of geometry and illumination. PAMI 20:1025\u20131039","journal-title":"PAMI"},{"key":"344_CR16","doi-asserted-by":"crossref","DOI":"10.21236\/ADA394631","volume-title":"Handbook of multisensor data fusion","author":"DL Hall","year":"2001","unstructured":"Hall DL, Llians J (2001) Handbook of multisensor data fusion. CRC, Boca Raton"},{"issue":"3 Part 1","key":"344_CR17","doi-asserted-by":"crossref","first-page":"1360","DOI":"10.1109\/36.763300","volume":"37","author":"LO Jimenez","year":"1999","unstructured":"Jimenez LO, Morales-Morell A, Creus A (1999) Classification of hyperdimensional data based on feature and decision fusion approaches using projection pursuit, majority voting, and neural networks. IEEE Trans Geosci Remote Sens 37(3 Part 1):1360\u20131366","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"4","key":"344_CR18","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1109\/TKDE.2005.66","volume":"17","author":"H Liu","year":"2005","unstructured":"Liu H, Yu L (2005) Toward integrating feature selection algorithms for classification and clustering. IEEE Trans Knowl Data Eng 17(4):491\u2013502","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"344_CR19","doi-asserted-by":"crossref","unstructured":"Mansoorizadeh M, Charkari NM (2008) Bimodal person-dependent emotion recognition: comparison of feature level and decision level information fusion. In: HCI\/HRI workshop, PETRA\u201908","DOI":"10.1145\/1389586.1389688"},{"key":"344_CR20","unstructured":"Mansoorizadeh M, Charkari NM (2009) Audiovisual emotion database in persian language (persian). In: CSI national conference, csicc 2009, CSI, Tehran"},{"key":"344_CR21","doi-asserted-by":"crossref","unstructured":"Martin O, Kotsia I, Macq B, Pitas I (2006) The enterface\u201905 audio-visual emotion database. In: Proc. 22nd intl. conf. on data engineering workshops (ICDEW\u201906)","DOI":"10.1109\/ICDEW.2006.145"},{"key":"344_CR22","first-page":"53","volume":"2","author":"A Mehrabian","year":"1968","unstructured":"Mehrabian A (1968) Communication without words. Psychol Today 2:53\u201356","journal-title":"Psychol Today"},{"key":"344_CR23","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1145\/1178745.1178762","volume-title":"Proceedings of the 1st ACM international workshop on human-centered multimedia","author":"M Paleari","year":"2006","unstructured":"Paleari M, Lisetti CL (2006) Toward multimodal fusion of affective cues. In: Proceedings of the 1st ACM international workshop on human-centered multimedia. ACM, New York, pp 99\u2013108"},{"key":"344_CR24","first-page":"124","volume":"22","author":"M Pantic","year":"2000","unstructured":"Pantic M, Rothkrantz LJM (2000) Automatic analysis of facial expressions: the state of the art. PAMI 22:124\u20131445","journal-title":"PAMI"},{"issue":"1\u20132","key":"344_CR25","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/S1071-5819(02)00141-6","volume":"59","author":"O Pierre-Yves","year":"2003","unstructured":"Pierre-Yves O (2003) The production and recognition of emotions in speech: features and algorithms. Int J Human-Comput Stud 59(1\u20132):157\u2013183","journal-title":"Int J Human-Comput Stud"},{"issue":"13","key":"344_CR26","doi-asserted-by":"crossref","first-page":"2115","DOI":"10.1016\/S0167-8655(03)00079-5","volume":"24","author":"A Ross","year":"2003","unstructured":"Ross A, Jain A (2003) Information fusion in biometrics. Pattern Recogn Lett 24(13):2115\u20132125","journal-title":"Pattern Recogn Lett"},{"issue":"10","key":"344_CR27","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1109\/TCSVT.2005.854237","volume":"15","author":"DA Sadlier","year":"2005","unstructured":"Sadlier DA, O\u2019Connor NE (2005) Event detection in field sports video using audio-visual features and a support vector machine. IEEE Trans Circuits Syst Video Technol 15(10):1225\u20131233","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"344_CR28","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/S0923-5965(97)00042-8","volume":"12","author":"K Sobottka","year":"1998","unstructured":"Sobottka K, Pitas I (1998) A novel method for automatic face segmentation, facial feature extraction and tracking. Signal Process Image Commun 12:263\u2013281","journal-title":"Signal Process Image Commun"},{"key":"344_CR29","doi-asserted-by":"crossref","first-page":"1913","DOI":"10.1016\/j.neucom.2007.07.041","volume":"71","author":"M Song","year":"1920","unstructured":"Song M, You M, Li N, Chen C (1920) A robust multimodal approach for emotion recognition. Neurocomputing 71:1913\u20132008","journal-title":"Neurocomputing"},{"key":"344_CR30","volume-title":"Statistical pattern recognition","year":"2002","unstructured":"Webb A (ed) (2002) Statistical pattern recognition. Wiley, New York"},{"key":"344_CR31","volume-title":"An introduction to the Kalman filter","author":"G Welch","year":"1995","unstructured":"Welch G, Bishop G (1995) An introduction to the Kalman filter, University of North Carolina at Chapel Hill, Chapel Hill"},{"key":"344_CR32","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1145\/1027527.1027665","volume-title":"Proceedings of the 12th annual ACM international conference on multimedia","author":"Y Wu","year":"2004","unstructured":"Wu Y, Chang EY, Chang KCC, Smith JR (2004) Optimal multimodal fusion for multimedia data analysis. In: Proceedings of the 12th annual ACM international conference on multimedia. ACM, New York, pp 572\u2013579"},{"issue":"6","key":"344_CR33","doi-asserted-by":"crossref","first-page":"1369","DOI":"10.1016\/S0031-3203(02)00262-5","volume":"36","author":"J Yang","year":"2003","unstructured":"Yang J, Yang J-y, Zhang D, Lu J-f (2003) Feature fusion: parallel strategy vs. serial strategy. Pattern Recogn 36(6):1369\u20131381","journal-title":"Pattern Recogn"},{"key":"344_CR34","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. PAMI 31:39\u201358","journal-title":"PAMI"},{"key":"344_CR35","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1016\/j.patcog.2003.09.006","volume":"37","author":"ZH Zhou","year":"2004","unstructured":"Zhou ZH, Geng X (2004) Projection functions for eye detection. Pattern Recogn 37:1049\u20131056","journal-title":"Pattern Recogn"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-009-0344-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-009-0344-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-009-0344-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T03:27:51Z","timestamp":1559359671000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-009-0344-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,8,20]]},"references-count":35,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2010,8]]}},"alternative-id":["344"],"URL":"https:\/\/doi.org\/10.1007\/s11042-009-0344-2","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,8,20]]}}}