{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:54:03Z","timestamp":1768341243123,"version":"3.49.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2016,7,19]],"date-time":"2016-07-19T00:00:00Z","timestamp":1468886400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100007225","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["MOST102-2221-E-006-094-MY3"],"award-info":[{"award-number":["MOST102-2221-E-006-094-MY3"]}],"id":[{"id":"10.13039\/100007225","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Ambient Intell Human Comput"],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1007\/s12652-016-0395-y","type":"journal-article","created":{"date-parts":[[2016,7,19]],"date-time":"2016-07-19T09:25:18Z","timestamp":1468920318000},"page":"895-906","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Coupled HMM-based multimodal fusion for mood disorder detection through elicited audio\u2013visual signals"],"prefix":"10.1007","volume":"8","author":[{"given":"Tsung-Hsien","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7588-7492","authenticated-orcid":false,"given":"Chung-Hsien","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun-Yi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Hsiang","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,7,19]]},"reference":[{"key":"395_CR1","doi-asserted-by":"crossref","unstructured":"American Psychiatric Association (2013) Diagnostic and statistical manual of mental disorders (DSM-5R): American Psychiatric Pub","DOI":"10.1176\/appi.books.9780890425596"},{"key":"395_CR2","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1192\/bjp.154.5.672","volume":"154","author":"TR Barnes","year":"1989","unstructured":"Barnes TR (1989) A rating scale for drug-induced akathisia. Br J Psychiatry 154:672\u2013676","journal-title":"Br J Psychiatry"},{"key":"395_CR3","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.2147\/NDT.S46525","volume":"9","author":"G Bersani","year":"2013","unstructured":"Bersani G, Polli E, Valeriani G, Zullo D, Melcore C, Capra E, Quartini A, Marino P, Minichino A, Bernabei L (2013) Facial expression in patients with bipolar disorder and schizophrenia in response to emotional stimuli: a partially shared cognitive and social deficit of the two disorders. J Neuropsychiatr Dis Treat 9:1137","journal-title":"J Neuropsychiatr Dis Treat"},{"key":"395_CR4","unstructured":"Bou-Ghazale SE, Assaleh K (2002) A robust endpoint detection of speech for noisy environments with application to automatic speech recognition. IEEE international conference on acoustics, speech, and signal processing (ICASSP), pp IV-3808\u2013IV-3811"},{"key":"395_CR5","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1176\/jnp.2007.19.4.436","volume":"19","author":"VP Bozikas","year":"2007","unstructured":"Bozikas VP, Kosmidis MH, Tonia T, Andreou C, Focas K, Karavatos A (2007) Impaired perception of affective prosody in remitted patients with bipolar disorder. J Neuropsychiatry Clin Neurosci 19:436\u2013440","journal-title":"J Neuropsychiatry Clin Neurosci"},{"key":"395_CR6","doi-asserted-by":"crossref","unstructured":"Brand M, Oliver N, Pentland A (1997) Coupled hidden Markov models for complex action recognition. In: Proc. Computer Vision Pattern Recognition, pp. 201\u2013206","DOI":"10.1109\/CVPR.1997.609450"},{"key":"395_CR7","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.biopsych.2005.06.008","volume":"59","author":"CH Chen","year":"2006","unstructured":"Chen CH, Lennox B, Jacob R, Calder A, Lupson V, Bisbrown-Chippendale R, Suckling J, Bullmore E (2006) Explicit and implicit facial affect recognition in manic and depressed states of bipolar disorder: a functional magnetic resonance imaging study. Biol Psychiatry 59:31\u201339","journal-title":"Biol Psychiatry"},{"key":"395_CR8","first-page":"555","volume":"55","author":"C Cheng","year":"2013","unstructured":"Cheng C, Chen H, Chan Y, Su Y, Tseng C (2013) Taiwan corpora of Chinese emotions and relevant psychophysiological data\u2014normative data for Chinese jokes. Chin J Psychol 55:555\u2013569","journal-title":"Chin J Psychol"},{"key":"395_CR9","doi-asserted-by":"crossref","unstructured":"Cohn JF, Kruez TS, Matthews I, Yang Y, Nguyen MH, Padilla MT, Zhou F, La Torre FD (2009) Detecting depression from facial actions and vocal prosody. In: Proc. IEEE international conference on affective computing and intelligent interaction and workshops, pp 1\u20137","DOI":"10.1109\/ACII.2009.5349358"},{"key":"395_CR10","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1016\/j.jad.2013.09.027","volume":"152","author":"DP David","year":"2014","unstructured":"David DP, Soeiro-de-Souza MG, Moreno RA, Bio DS (2014) Facial emotion recognition and its correlation with executive functions in bipolar I patients and healthy controls. J Affect Disord 152:288\u2013294","journal-title":"J Affect Disord"},{"key":"395_CR11","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1002\/0470013494.ch3","volume-title":"Handbook of cognition and emotion","author":"P Ekman","year":"1999","unstructured":"Ekman P (1999) Basic emotions. Handbook of cognition and emotion. Wiley, New York, pp 45\u201360"},{"key":"395_CR12","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1007\/s00521-015-1959-z","volume":"27","author":"TT Erguzel","year":"2016","unstructured":"Erguzel TT, Sayar GH, Tarhan N (2016) Artificial intelligence approach to classify unipolar and bipolar depressive disorders. Neural Comput Appl 27:1607\u20131616","journal-title":"Neural Comput Appl"},{"key":"395_CR13","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 international conference on multimedia, 2010, pp. 1459\u20131462","DOI":"10.1145\/1873951.1874246"},{"issue":"12","key":"395_CR14","doi-asserted-by":"crossref","first-page":"1923","DOI":"10.1109\/29.45538","volume":"37","author":"S Furui","year":"1989","unstructured":"Furui S (1989) Unsupervised speaker adaptation based on hierarchical spectral clustering. IEEE Trans Acoust Speech Signal Process 37(12):1923\u20131930","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"395_CR15","unstructured":"Giannakopoulos T (2009) A method for silence removal and segmentation of speech signals, implemented in Matlab, Department of Informatics and Telecommunications, University of Athens, Greece, Computational Intelligence Laboratory (CIL), Insititute of Informatics and Telecommunications (IIT), NCSR DEMOKRITOS, Greece"},{"key":"395_CR16","unstructured":"Glorot X, Bordes A, Bengio Y (2011) Domain adaptation for large-scale sentiment classification: a deep learning approach. In: Proceedings of the 28th international conference on machine learning (ICML-11) pp. 513\u2013520"},{"key":"395_CR17","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1016\/j.comppsych.2012.10.012","volume":"54","author":"VM Goghari","year":"2013","unstructured":"Goghari VM, Sponheim SR (2013) More pronounced deficits in facial emotion recognition for schizophrenia than bipolar disorder. Compr Psychiatry 54:388\u2013397","journal-title":"Compr Psychiatry"},{"issue":"6","key":"395_CR18","doi-asserted-by":"crossref","first-page":"1865","DOI":"10.1109\/JBHI.2014.2300940","volume":"18","author":"A Greco","year":"2014","unstructured":"Greco A, Valenza G, Lanata A, Rota G, Scilingo EP (2014) Electrodermal activity in bipolar patients during affective elicitation. IEEE J Biomed Health Inform 18(6):1865\u20131873","journal-title":"IEEE J Biomed Health Inform"},{"key":"395_CR19","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1080\/02699939508408966","volume":"9","author":"JJ Gross","year":"1995","unstructured":"Gross JJ, Levenson RW (1995) Emotion elicitation using films. Cogn Emot 9:87\u2013108","journal-title":"Cogn Emot"},{"issue":"1","key":"395_CR20","doi-asserted-by":"crossref","first-page":"68","DOI":"10.4018\/jse.2010101605","volume":"1","author":"H Gunes","year":"2010","unstructured":"Gunes H, Pantic M (2010) Automatic, dimensional and continuous emotion recognition. Int J Synth Emot (IJSE) 1(1):68\u201399","journal-title":"Int J Synth Emot (IJSE)"},{"key":"395_CR21","unstructured":"Guy W (1976) Clinical global impression scale, The ECDEU assessment manual for psychopharmacology-revised. Volume DHEW Publ No ADM 76, vol 338, pp. 218\u2013222"},{"key":"395_CR22","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1136\/jnnp.23.1.56","volume":"23","author":"M Hamilton","year":"1960","unstructured":"Hamilton M (1960) A rating scale for depression. J Neurol Neurosurg Psychiatry 23:56","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"395_CR23","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1109\/89.326616","volume":"2","author":"H Hermansky","year":"1994","unstructured":"Hermansky H, Morgan N (1994) RASTA processing of speech. IEEE Trans Speech Audio Process 2:578\u2013589","journal-title":"IEEE Trans Speech Audio Process"},{"key":"395_CR24","doi-asserted-by":"crossref","first-page":"1873","DOI":"10.1176\/appi.ajp.157.11.1873","volume":"157","author":"RM Hirschfeld","year":"2000","unstructured":"Hirschfeld RM, Williams JB, Spitzer RL, Calabrese JR, Flynn L, Keck PE Jr, Lewis L, McElroy SL, Post RM, Rapport DJ (2000) Development and validation of a screening instrument for bipolar spectrum disorder: the mood disorder questionnaire. Am J Psychiatry 157:1873\u20131875","journal-title":"Am J Psychiatry"},{"key":"395_CR25","doi-asserted-by":"crossref","unstructured":"Howard N (2013) Approach towards a natural language analysis for diagnosing mood disorders and comorbid conditions. In: Proc. mexican international conference on artificial intelligence (MICAI), pp. 234\u2013243","DOI":"10.1109\/MICAI.2013.50"},{"key":"395_CR26","doi-asserted-by":"crossref","unstructured":"Lanata A, Greco A, Valenza G, Scilingo EP (2014) A pattern recognition approach based on electrodermal response for pathological mood identification in bipolar disorders. In: Proc. IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 3601\u20133605","DOI":"10.1109\/ICASSP.2014.6854272"},{"key":"395_CR27","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1080\/13803390490490515720","volume":"27","author":"SA Langenecker","year":"2005","unstructured":"Langenecker SA, Bieliauskas LA, Rapport LJ, Zubieta JK, Wilde EA, Berent S (2005) Face emotion perception and executive functioning deficits in depression. J Clin Exp Neuropsychol 27:320\u2013333","journal-title":"J Clin Exp Neuropsychol"},{"key":"395_CR28","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/S0920-9964(98)00105-4","volume":"35","author":"S Leucht","year":"1999","unstructured":"Leucht S, Pitschel-Walz G, Abraham D, Kissling W (1999) Efficacy and extrapyramidal side-effects of the new antipsychotics olanzapine, quetiapine, risperidone, and sertindole compared to conventional antipsychotics and placebo. A meta-analysis of randomized controlled trials. Schizophr Res 35:51\u201368","journal-title":"Schizophr Res"},{"key":"395_CR29","doi-asserted-by":"crossref","unstructured":"Low LSA, Maddage NC, Lech M, Sheeber L, Allen NB (2010) Influence of acoustic low-level descriptors in the detection of clinical depression in adolescents. In: Proc. IEEE international conference on acoustics speech and signal processing (ICASSP), pp. 5154\u20135157","DOI":"10.1109\/ICASSP.2010.5495018"},{"issue":"3","key":"395_CR30","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1109\/TBME.2010.2091640","volume":"58","author":"LSA Low","year":"2011","unstructured":"Low LSA, Maddage NC, Lech M, Sheeber L, Allen NB (2011) Detection of clinical depression in adolescents\u2019 speech during family interactions. IEEE Trans Biomed Eng 58(3):574\u2013586","journal-title":"IEEE Trans Biomed Eng"},{"key":"395_CR31","doi-asserted-by":"crossref","unstructured":"Lucey P, Cohn JF, Kanade T, Saragih J, Ambadar Z, Matthews I (2010) The extended Cohn-Kanade dataset (CK+): a complete dataset for action unit and emotion-specified expression. IEEE computer society conference on computer vision and pattern recognition workshops (CVPRW), pp. 94\u2013101","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"395_CR32","unstructured":"Martin O, Kotsia I, Macq B, Pitas I (2006) The eNTERFACE\u201905 audio-visual emotion database. In: Proceedings of the 22nd international conference on data engineering workshops (ICDEW\u201906), Atlanta, USA, 3\u20137 April 2006"},{"issue":"2","key":"395_CR33","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1109\/TBME.2012.2228646","volume":"60","author":"KEB Ooi","year":"2013","unstructured":"Ooi KEB, Lech M, Allen NB (2013) Multichannel weighted speech classification system for prediction of major depression in adolescents. IEEE Trans Biomed Eng 60(2):497\u2013506","journal-title":"IEEE Trans Biomed Eng"},{"key":"395_CR34","first-page":"S271","volume":"11","author":"RH Perlis","year":"2005","unstructured":"Perlis RH (2005) Misdiagnosis of bipolar disorder. Am J Managed Care 11:S271\u2013S274","journal-title":"Am J Managed Care"},{"key":"395_CR35","doi-asserted-by":"crossref","unstructured":"Rattani A, Kisku DR, Bicego M, Tistarelli M (2007) Feature level fusion of face and fingerprint biometrics. In: Proceedings of the first IEEE international conference on biometrics: theory, applications, and systems, 2007, BTAS 2007, IEEE, pp 1\u20136","DOI":"10.1109\/BTAS.2007.4401919"},{"key":"395_CR36","doi-asserted-by":"crossref","unstructured":"Rezek L, Sykacek P, Roberts SJ (2000) Learning interaction dynamics with coupled hidden Markov models. IEE proceedings\u2014science, measurement and technology, vol 147. no. 6","DOI":"10.1049\/ip-smt:20000851"},{"key":"395_CR37","unstructured":"Saha G, Chakroborty S, Senapati S (2005) A new silence removal and endpoint detection algorithm for speech and speaker recognition applications. In: Proceedings of the 11th national conference on communications (NCC), pp. 291\u2013295"},{"key":"395_CR38","doi-asserted-by":"crossref","unstructured":"Sanchez MH, Vergyri D, Ferrer L, Richey C, Garcia P, Knoth B, Jarrold W (2011) Using prosodic and spectral features in detecting depression in elderly males. In: Proc. INTERSPEECH, pp. 3001\u20133004","DOI":"10.21437\/Interspeech.2011-751"},{"key":"395_CR39","doi-asserted-by":"crossref","unstructured":"Schuller B, Valstar M, Eyben F, McKeown G, Cowie R, Pantic M (2011) AVEC 2011 the first international audio\/visual emotion challenge. In: Proc. First int. audio\/visual emotion challenge and workshop (ACII), pp. 415\u2013424","DOI":"10.1007\/978-3-642-24571-8_53"},{"key":"395_CR40","doi-asserted-by":"crossref","unstructured":"Schuller B, Valstar M, Eyben F, Cowie R, Pantic M (2012) AVEC 2012\u2014the continuous audio\/visual emotion challenge. In: Proc. of int. audio\/visual emotion challenge and workshop (AVEC), ACM ICMI","DOI":"10.1145\/2388676.2388758"},{"key":"395_CR41","doi-asserted-by":"crossref","first-page":"1799","DOI":"10.1017\/S0033291706008804","volume":"36","author":"M Summers","year":"2006","unstructured":"Summers M, Papadopoulou K, Bruno S, Cipolotti L, Ron MA (2006) Bipolar I and bipolar II disorder: cognition and emotion processing. Psychol Med 36:1799\u20131809","journal-title":"Psychol Med"},{"key":"395_CR42","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1037\/0894-4105.18.2.212","volume":"18","author":"SA Surguladze","year":"2004","unstructured":"Surguladze SA, Young AW, Senior C, Br\u00e9bion G, Travis MJ, Phillips ML (2004) Recognition accuracy and response bias to happy and sad facial expressions in patients with major depression. Neuropsychology 18:212","journal-title":"Neuropsychology"},{"key":"395_CR43","doi-asserted-by":"crossref","unstructured":"Tzimiropoulos G, Pantic M (2014) Gauss-newton deformable part models for face alignment in-the-wild. In: Computer vision and pattern recognition (CVPR), 2014 IEEE conference, pp. 1851\u20131858","DOI":"10.1109\/CVPR.2014.239"},{"key":"395_CR44","doi-asserted-by":"crossref","unstructured":"Valstar M, Schuller B, Smith K, Eyben F, Jiang B, Bilakhia S et al (2013) AVEC 2013: the continuous audio\/visual emotion and depression recognition challenge. In: Proceedings of the 3rd ACM international workshop on audio\/visual emotion challenge, ACM, pp 3\u201310","DOI":"10.1145\/2512530.2512533"},{"key":"395_CR45","doi-asserted-by":"crossref","first-page":"1027","DOI":"10.1016\/j.cortex.2011.03.017","volume":"48","author":"AC Vederman","year":"2012","unstructured":"Vederman AC, Weisenbach SL, Rapport LJ, Leon HM, Haase BD, Franti LM, Schallmo MP, Saunders EF, Kamali MM, Zubieta JK (2012) Modality-specific alterations in the perception of emotional stimuli in bipolar disorder compared to healthy controls and major depressive disorder. Cortex 48:1027\u20131034","journal-title":"Cortex"},{"key":"395_CR46","unstructured":"Wu CH, Lin JC, Wei WL (2014) A survey on audiovisual emotion recognition: databases, features, and data fusion strategies. APSIPA transactions on signal and information processing, vol. 3, e12"},{"key":"395_CR47","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1192\/bjp.133.5.429","volume":"133","author":"R Young","year":"1978","unstructured":"Young R, Biggs J, Ziegler V, Meyer D (1978) A rating scale for mania: reliability, validity and sensitivity. Br J Psychiatry 133:429\u2013435","journal-title":"Br J Psychiatry"},{"key":"395_CR48","doi-asserted-by":"crossref","unstructured":"Zeng Z, Pantic M, Roisman G, Huang TS (2009) A survey of affect recognition methods: audio, visual, and spontaneous expressions. IEEE transactions on pattern analysis and machine intelligence, 31.1 pp. 39\u201358","DOI":"10.1109\/TPAMI.2008.52"}],"container-title":["Journal of Ambient Intelligence and Humanized Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12652-016-0395-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-016-0395-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-016-0395-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-016-0395-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T08:53:48Z","timestamp":1718700828000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12652-016-0395-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7,19]]},"references-count":48,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2017,11]]}},"alternative-id":["395"],"URL":"https:\/\/doi.org\/10.1007\/s12652-016-0395-y","relation":{},"ISSN":["1868-5137","1868-5145"],"issn-type":[{"value":"1868-5137","type":"print"},{"value":"1868-5145","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,7,19]]}}}