{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T10:59:13Z","timestamp":1791111553138,"version":"4.1.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,9,7]],"date-time":"2013-09-07T00:00:00Z","timestamp":1378512000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Multimodal User Interfaces"],"published-print":{"date-parts":[[2013,11]]},"DOI":"10.1007\/s12193-013-0123-2","type":"journal-article","created":{"date-parts":[[2013,9,6]],"date-time":"2013-09-06T20:56:49Z","timestamp":1378501009000},"page":"217-228","source":"Crossref","is-referenced-by-count":149,"title":["Multimodal assistive technologies for depression diagnosis and monitoring"],"prefix":"10.1007","volume":"7","author":[{"given":"Jyoti","family":"Joshi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roland","family":"Goecke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sharifa","family":"Alghowinem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhinav","family":"Dhall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Wagner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julien","family":"Epps","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gordon","family":"Parker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Breakspear","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2013,9,7]]},"reference":[{"key":"123_CR1","unstructured":"Alghowinem S, Goecke R, Wagner M, Epps J, Breakspear M, Parker G (2012) From joyous to clinically depressed: mood detection using spontaneous speech. In: Proceedings of the 25th international FLAIRS conference FLAIRS-25, pp 141\u2013146"},{"issue":"5","key":"123_CR2","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1111\/j.0956-7976.2005.01548.x","volume":"16","author":"Z Ambadar","year":"2005","unstructured":"Ambadar Z, Schooler J, Cohn J (2005) Deciphering the enigmatic face: the importance of facial dynamics to interpreting subtle facial expressions. Psychol Sci 16(5):403\u2013410","journal-title":"Psychol Sci"},{"key":"123_CR3","doi-asserted-by":"crossref","unstructured":"Asthana A, Saragih J, Wagner M, Goecke R (2009) Evaluating AAM fitting methods for facial expression recognition. In: Proceedings of the IEEE international conference on affective computing and intelligent interaction ACII2009, pp 598\u2013605","DOI":"10.1109\/ACII.2009.5349489"},{"key":"123_CR4","doi-asserted-by":"crossref","unstructured":"Batliner A, Huber R (2007) Speaker classification I. Speaker characteristics and emotion classification, Springer, Verlag, pp 138\u2013151","DOI":"10.1007\/978-3-540-74200-5_7"},{"key":"123_CR5","doi-asserted-by":"crossref","unstructured":"Busso C, Deng Z, Yildirim S, Bulut M, Lee CM, Kazemzadeh A, Lee S, Neumann U, Narayanan S (2004) Analysis of emotion recognition using facial expressions, speech and multimodal information. In: Sixth international conference on multimodal interfaces ICMI 2004, ACM Press, New York, pp 205\u2013211","DOI":"10.1145\/1027933.1027968"},{"key":"123_CR6","unstructured":"Chang CC, Lin CJ (2001) LIBSVM: a library for support vector machines. http:\/\/www.csie.ntu.edu.tw\/cjlin\/libsvm"},{"key":"123_CR7","doi-asserted-by":"crossref","unstructured":"Cohn JF, Kreuz TS, Matthews I, Yang Y, Nguyen MH, Padilla MT, Zhou F, De la Torre F (2009) Detecting depression from facial actions and vocal prosody. In: Proceedings of international conference on affective computing and intelligent interaction ACII2009, pp 1\u20137","DOI":"10.1109\/ACII.2009.5349358"},{"key":"123_CR8","doi-asserted-by":"crossref","unstructured":"Cummins N, Epps J, Breakspear M, Goecke R (2011) An investigation of depressed speech detection: features and normalization. In: Proceedings of interspeech 2011, pp 2997\u20133000","DOI":"10.21437\/Interspeech.2011-750"},{"key":"123_CR9","doi-asserted-by":"crossref","unstructured":"Dhall A, Asthana A, Goecke R (2010) Facial expression based automatic album creation. In: Proceedings of international conference on neural information processing ICONIP2010, lecture notes of computer science 6444, pp 485\u2013492","DOI":"10.1007\/978-3-642-17534-3_60"},{"key":"123_CR10","doi-asserted-by":"crossref","unstructured":"Dhall A, Asthana A, Goecke R, Gedeon T (2011) Emotion recognition using PHOG and LPQ features. In: Proceedings of IEEE international conference on automatic face and gesture recognition FG2011, workshop facial expression recognition and analysis, FERA2011, pp 878\u2013883","DOI":"10.1109\/FG.2011.5771366"},{"key":"123_CR11","unstructured":"Dhall A, Joshi J, Radwan I, Goecke R (2012) Finding happiest moments in a social context. In: Proceedings of Asian conference on computer vision ACCV2012, LNCS 7725, pp 613\u2013626"},{"key":"123_CR12","doi-asserted-by":"crossref","unstructured":"Edwards G, Taylor C, Cootes T (1998) Interpreting face images using active appearance models. In: Proceedings of the IEEE international conference on automatic face and gesture recognition FG\u201998, IEEE, Nara, pp 300\u2013305","DOI":"10.1109\/AFGR.1998.670965"},{"key":"123_CR13","unstructured":"Ellgring H (2008) Nonverbal communication in depression. Cambridge University Press, Cambridge"},{"issue":"2","key":"123_CR14","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/BF02253071","volume":"20","author":"H Ellgring","year":"1996","unstructured":"Ellgring H, Scherer KR (1996) Vocal indicators of mood change in depression. J Nonverbal Behav 20(2):83\u2013110","journal-title":"J Nonverbal Behav"},{"key":"123_CR15","unstructured":"Everingham M, Sivic J, Zisserman A (2006) Hello! My name is... Buffy\u2014automatic naming of characters in TV Video. In: Proceedings of the British machine vision conference BMVC2006, Edinburgh, pp 899\u2013908"},{"key":"123_CR16","doi-asserted-by":"crossref","unstructured":"Eyben F, W\u00f6llmer M, Schuller B (2010) Opensmile: the munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM international conference on multimedia (MM\u201910), Firenze, pp 1459\u20131462","DOI":"10.1145\/1873951.1874246"},{"key":"123_CR17","unstructured":"Joshi J, Dhall A, Goecke R, Breakspear M, Parker G (2012) Neural-net classification for spatio-temporal descriptor based depression analysis. In: Proceedings of the international conference on pattern recognition ICPR2012, Tsukuba, pp 2634\u20132638"},{"key":"123_CR18","doi-asserted-by":"crossref","unstructured":"Joshi J, Goecke R, Breakspear M, Parker G (2013) Can body expressions contribute to automatic depression analysis? In: Proceedings of the 10th IEEE international conference on automatic face and gesture recognition FG2013 . Shanghai, China","DOI":"10.1109\/FG.2013.6553796"},{"key":"123_CR19","doi-asserted-by":"crossref","unstructured":"Kessler R, Berglund P, Demler O, Jin R, Koretz D, Merikangas K, Rush A, Walters E, Wang P (2003) The epidemiology of major depressive disorder: results from the national comorbidity survey replication (NCS-R). J Am Med Assoc 289(23): 3095\u20133105","DOI":"10.1001\/jama.289.23.3095"},{"issue":"3","key":"123_CR20","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1016\/0022-3956(93)90040-9","volume":"27","author":"S Kuny","year":"1993","unstructured":"Kuny S, Stassen HH (1993) Speaking behavior and voice sound characteristics in depressive patients during recovery. J Psychiatr Res 27(3):289\u2013307","journal-title":"J Psychiatr Res"},{"key":"123_CR21","doi-asserted-by":"crossref","unstructured":"Laptev I, Marsza\u0142ek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies. In: Proceedings of IEEE conference on computer vision and pattern recognition CVPR2008, pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"123_CR22","doi-asserted-by":"crossref","unstructured":"Lingenfelser F, Wagner J, Andr\u00e9 E (2011) A systematic discussion of fusion techniques for multi-modal affect recognition tasks. In: Proceedings of the 13th international conference on multimodal interfaces ICMI2011, ACM, Alicante, pp 19\u201326","DOI":"10.1145\/2070481.2070487"},{"key":"123_CR23","doi-asserted-by":"crossref","unstructured":"Lucey S, Matthews I, Hu C, Ambadar Z, de la Torre F, Cohn J (2006) AAM derived face representations for robust facial action recognition. In: Proceedings of the IEEE international conference on automatic face and gesture recognition FG2006, Southampton, pp 155\u2013162","DOI":"10.1109\/FGR.2006.17"},{"key":"123_CR24","unstructured":"Mathers C, Boerma T, Fat DM (2004) The global burden of disease: 2004 update. Technical report, WHO Press, Switzerland"},{"key":"123_CR25","doi-asserted-by":"crossref","unstructured":"McIntyre G, Goecke R, Hyett M, Green M, Breakspear M (2009) An approach for automatically measuring facial activity in depressed subjects. In: Proceedings of international conference on affective computing and intelligent interaction ACII2009, Amsterdam, pp 223\u2013230","DOI":"10.1109\/ACII.2009.5349593"},{"key":"123_CR26","doi-asserted-by":"crossref","unstructured":"Moore E, Clements M, Peifer J, Weisser L (2004) Comparing objective feature statistics of speech for classifying clinical depression. In: Proceedings of 26th annual international conference of the IEEE engineering in medicine and biology society IEMBS\u201904 1, pp 17\u201320","DOI":"10.1109\/IEMBS.2004.1403079"},{"key":"123_CR27","doi-asserted-by":"crossref","unstructured":"Moore E, Clements M, Peifer J, Weisser L (2008) Critical analysis of the impact of glottal features in the classification of clinical depression in speech. In: IEEE transactions on biomedical engineering 55, pp 96\u2013107","DOI":"10.1109\/TBME.2007.900562"},{"issue":"1","key":"123_CR28","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.jneuroling.2006.04.001","volume":"20","author":"JC Mundt","year":"2007","unstructured":"Mundt JC, Snyder PJ, Cannizzaro MS, Chappie K, Geralts DS (2007) Voice acoustic measures of depression severity and treatment response collected via interactive voice response (IVR) technology. J Neurolinguistics 20(1):50\u201364","journal-title":"J Neurolinguistics"},{"key":"123_CR29","doi-asserted-by":"crossref","unstructured":"Nilsonne A (1988) Speech characteristics as indicators of depressive illness. Acta Psychiatrica Scandinavica 77(3):253\u2013263","DOI":"10.1111\/j.1600-0447.1988.tb05118.x"},{"key":"123_CR30","doi-asserted-by":"crossref","unstructured":"Ozdas A, Shiavi R, Silverman S, Silverman M, Wilkes D (2000) Analysis of fundamental frequency for near term suicidal risk assessment. In: Proceedings of the 2000 IEEE international conference on systems, man and cybernetics SMC2000, vol 3, pp 1853\u20131858","DOI":"10.1109\/ICSMC.2000.886379"},{"issue":"12","key":"123_CR31","doi-asserted-by":"crossref","first-page":"1424","DOI":"10.1109\/34.895976","volume":"22","author":"M Pantic","year":"2000","unstructured":"Pantic M, Rothkrantz L (2000) Automatic analysis of facial expressions: the state of the art. IEEE Trans Pattern Anal Mach Intell 22(12):1424\u20131445","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"123_CR32","doi-asserted-by":"crossref","unstructured":"Parker G, Hadzi-Pavlovic D (1996) Melancholia: a disorder of movement and mood. Cambridge University Press, Cambridge","DOI":"10.1017\/CBO9780511759024"},{"key":"123_CR33","doi-asserted-by":"crossref","DOI":"10.1037\/e526112012-054","volume-title":"Affective computing","author":"R Picard","year":"1997","unstructured":"Picard R (1997) Affective computing. MIT Press, Cambridge"},{"key":"123_CR34","unstructured":"Prendergast M (2006) Understanding depression. Penguin, Australia"},{"issue":"11","key":"123_CR35","doi-asserted-by":"crossref","first-page":"2628","DOI":"10.1016\/j.patcog.2009.04.014","volume":"42","author":"J Saragih","year":"2009","unstructured":"Saragih J, Goecke R (2009) Learning AAM fitting through simulation. Pattern Recognit 42(11):2628\u20132636","journal-title":"Pattern Recognit"},{"key":"123_CR36","doi-asserted-by":"crossref","unstructured":"Saragih JM, Lucey S, Cohn J (2009) Face alignment through subspace constrained mean-shifts. In: Proceedings of the IEEE international conference of computer vision ICCV2009, pp 1034\u20131041","DOI":"10.1109\/ICCV.2009.5459377"},{"key":"123_CR37","unstructured":"Scherer KR (1987) Vocal assessment of affective disorders. In: Maser JD (ed) Depression and expressive behavior, Lawrence Erlbaum Associates, pp 57\u201382"},{"key":"123_CR38","doi-asserted-by":"crossref","unstructured":"Schuller B, Batliner A, Seppi D, Steidl S, Vogt T, Wagner J, Devillers L, Vidrascu L, Amir N, Kessous L (2007) The relevance of feature type for the automatic classification of emotional user states: low level descriptors and functionals. In: Proceedings of interspeech 2007, Antwerp, Belgium, pp 2253\u20132256","DOI":"10.21437\/Interspeech.2007-612"},{"key":"123_CR39","doi-asserted-by":"crossref","unstructured":"Sikka K, Wu T, Susskind J, Bartlett MS (2012) Exploring bag of words architectures in the facial expression domain. In: Proceedings of the European conference on computer vision (ECCV) workshops, lecture notes in computer science 7584, Springer, Verlag, pp 250\u2013259","DOI":"10.1007\/978-3-642-33868-7_25"},{"key":"123_CR40","unstructured":"Viola PA, Jones MJ (2001) Rapid object detection using a boosted cascade of simple features. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition CVPR2001, pp 511\u2013518"},{"key":"123_CR41","doi-asserted-by":"crossref","unstructured":"Zeng Z, Pantic M, Roisman G, Huang T (2009) A survey of affect recognition methods: audio, visual, and spontaneous expressions. IEEE Trans Pattern Anal Mach Intell 31(1):39\u201358","DOI":"10.1109\/TPAMI.2008.52"},{"key":"123_CR42","doi-asserted-by":"crossref","unstructured":"Zhao G, Pietikainen M (2007) Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans Pattern Anal Mach Intell 31(1):39\u201358","DOI":"10.1109\/TPAMI.2007.1110"},{"key":"123_CR43","unstructured":"Zhu X, Ramanan D (2012) Face detection, pose estimation, and landmark localization in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition CVPR2012, Providence, USA, pp 2879\u20132886"}],"container-title":["Journal on Multimodal User Interfaces"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12193-013-0123-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12193-013-0123-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12193-013-0123-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,5]],"date-time":"2022-03-05T18:13:28Z","timestamp":1646504008000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12193-013-0123-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,9,7]]},"references-count":43,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,11]]}},"alternative-id":["123"],"URL":"https:\/\/doi.org\/10.1007\/s12193-013-0123-2","relation":{},"ISSN":["1783-7677","1783-8738"],"issn-type":[{"value":"1783-7677","type":"print"},{"value":"1783-8738","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,9,7]]}}}