{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T23:45:26Z","timestamp":1776728726058,"version":"3.51.2"},"reference-count":103,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2012,11,9]],"date-time":"2012-11-09T00:00:00Z","timestamp":1352419200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"published-print":{"date-parts":[[2015,2]]},"DOI":"10.1007\/s10462-012-9368-5","type":"journal-article","created":{"date-parts":[[2012,11,8]],"date-time":"2012-11-08T04:34:35Z","timestamp":1352349275000},"page":"155-177","source":"Crossref","is-referenced-by-count":335,"title":["Features and classifiers for emotion recognition from speech: a survey from 2000 to 2011"],"prefix":"10.1007","volume":"43","author":[{"given":"Christos-Nikolaos","family":"Anagnostopoulos","sequence":"first","affiliation":[]},{"given":"Theodoros","family":"Iliou","sequence":"additional","affiliation":[]},{"given":"Ioannis","family":"Giannoukos","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,11,9]]},"reference":[{"key":"9368_CR1","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.psychres.2005.12.006","volume":"149","author":"M Aigner","year":"2007","unstructured":"Aigner M, Sachs G, Bruckm\u00fcller E, Winklbaur B, Zitterl W, Kryspin-Exner I, Gur R, Katschnig H (2007) Cognitive and emotion recognition deficits in obsessive\u2013compulsive disorder. Psychiatr Res 149: 121\u2013128","journal-title":"Psychiatr Res"},{"key":"9368_CR2","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1007\/978-3-642-11684-1_8","volume":"279","author":"CN Anagnostopoulos","year":"2010","unstructured":"Anagnostopoulos CN, Iliou T (2010) Towards emotion recognition from speech: definition, problems and the materials of research. Stud Comput Intell 279: 127\u2013143","journal-title":"Stud Comput Intell"},{"key":"9368_CR3","unstructured":"Anagnostopoulos CN, Vovoli E (2010) Sound processing features for speaker-dependent and phrase-independent emotion recognition in Berlin Database. In: Papadopoulos GA, Wojtkowski W, Wojtkowski G, Wrycza S, Zupancic J (eds) Information systems development, pp 413\u2013421"},{"key":"9368_CR4","doi-asserted-by":"crossref","unstructured":"Ang J, Dhillon R, Shriberg E, Stolcke A (2002) Prosody-based automatic detection of annoyance and frustration in human\u2013computer dialog. In: Proceedings of interspeech, pp 2037\u20132040","DOI":"10.21437\/ICSLP.2002-559"},{"key":"9368_CR5","doi-asserted-by":"crossref","unstructured":"Atassi H, Esposito A (2008) A speaker independent approach to the classification of emotional vocal expressions. In: Proceedings of 20th IEEE international conference on tools with artificial intelligence, pp 147\u2013152","DOI":"10.1109\/ICTAI.2008.158"},{"key":"9368_CR6","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1016\/j.neunet.2005.03.008","volume":"18","author":"T Athanaselis","year":"2005","unstructured":"Athanaselis T, Bakamidis S, Dologlou I, Cowie R, Douglas-Cowie E, Cox C (2005) ASR for emotional speech: clarifying the issues and enhancing performance. Neural Netw 18: 437\u2013444","journal-title":"Neural Netw"},{"key":"9368_CR7","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/S0167-6393(02)00079-1","volume":"40","author":"A Batliner","year":"2003","unstructured":"Batliner A, Fischer K, Huber R, Spilker J, Nolth E (2003) How to find trouble in communication. Speech Commun 40: 117\u2013143","journal-title":"Speech Commun"},{"key":"9368_CR8","unstructured":"Batliner A, Steidl S, Schuller B, Seppi D, Laskowski K, Vogt T, Devillers L, Vidrascu L, Amir N, Kessous L, Aharonson V (2006) Combining efforts for improving automatic classification of emotional user states. In: Proceedings of 1st international language technologies conference, pp 240\u2013245"},{"key":"9368_CR9","unstructured":"Bogert B, Healy M, Tukey J (1963) The quefrency analysis of time series for echoes: cepstrum, pseudo-autocovariance, cross-cepstrum and saphe cracking. In: Rosenblatt M (ed) Symposium on time series analysis. Wiley, New York, pp 209\u2013243"},{"key":"9368_CR10","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1038\/35072584","volume":"2","author":"J Calder","year":"2001","unstructured":"Calder J, Lawrence AD, Young AW (2001) Neuropsychology of fear and loathing. Nat Rev Neurosci 2: 352\u2013363","journal-title":"Nat Rev Neurosci"},{"key":"9368_CR11","doi-asserted-by":"crossref","unstructured":"Cheng XM, Cheng PY, Zhao L (2009) A study on emotional feature analysis and recognition in speech signal. In: Proceedings of international conference on measuring technology and mechatronics automation, pp 418\u2013420","DOI":"10.1109\/ICMTMA.2009.89"},{"key":"9368_CR12","doi-asserted-by":"crossref","unstructured":"Cen L, Ser W, Yu ZL (2008) Speech emotion recognition using canonical correlation analysis and probabilistic neural network. In: Proceedings of 7th international conference on machine learning and applications, pp 859\u2013862","DOI":"10.1109\/ICMLA.2008.85"},{"key":"9368_CR13","unstructured":"Cowie R, Douglas-Cowie E, Savvidou S, McMahon E, Sawey M, Schroder M (2000) FEELTRACE: an instrument for recording perceived emotion in real time. In: Proceedings of ISCA speech and emotion workshop, pp 19\u201324"},{"key":"9368_CR14","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/j.neunet.2005.03.002","volume":"18","author":"R Cowie","year":"2005","unstructured":"Cowie R, Douglas-Cowie E, Cox C (2005) Beyond emotion archetypes: databases for emotion modelling using neural networks. Neural Netw 18: 371\u2013388","journal-title":"Neural Netw"},{"key":"9368_CR15","unstructured":"Devillers L, Vasilescu I, Lamel L (2003) Emotion detection in task oriented spoken dialogs. In: Proceedings of IEEE multimedia human\u2013machine interface and interaction conference, pp 549\u2013552"},{"key":"9368_CR16","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/S0167-6393(02)00070-5","volume":"40","author":"E Douglas-Cowie","year":"2003","unstructured":"Douglas-Cowie E, Campbell N, Cowie R, Roach P (2003) Emotional speech: towards a new generation of databases. Speech Commun 40: 33\u201360","journal-title":"Speech Commun"},{"key":"9368_CR17","doi-asserted-by":"crossref","unstructured":"Douglas-Cowie E, Cowie R, Sneddon I, Cox C, Lowry O, McRorie M, Martin JC, Devillers L, Abrilan S, Batliner A, Amir N, Karpouzis K (2007) The HUMAINE database: addressing the collection and annotation of naturalistic and induced emotional data. In: Proceedings of international conference affective computing and intelligent interaction, pp 488\u2013500","DOI":"10.1007\/978-3-540-74889-2_43"},{"key":"9368_CR18","doi-asserted-by":"crossref","unstructured":"Dumouche P, Dehak N, Attabi Y, Dehak R, Boufaden N (2009) Cepstral and long-term features for emotion recognition. In: Proceedings of INTERSPEECH, pp 344\u2013347","DOI":"10.21437\/Interspeech.2009-111"},{"key":"9368_CR19","doi-asserted-by":"crossref","unstructured":"Fernandez R, Picard RW (2003) Modeling drivers\u2019 speech under stress. Speech Communications, vol 40. Elsevier, pp 145\u2013159","DOI":"10.1016\/S0167-6393(02)00080-8"},{"key":"9368_CR20","unstructured":"Firoz Shah A, Vimal Krishnan VR, Raji Sukumar A, Jayakumar A, Babu Anto P (2009) Speaker independent automatic emotion recognition from speech: a comparison of MFCCs and discrete wavelet transforms. In: Proceedings of international conference on advances in recent technologies in communication and computing, pp 528\u2013531"},{"key":"9368_CR21","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1111\/j.1467-9280.2007.02024.x","volume":"18","author":"JRJ Fontaine","year":"2010","unstructured":"Fontaine JRJ, Scherer KR, Roesch EB, Ellsworth PC (2010) The world of emotions is not two dimensional. Psychol Sci 18: 1050\u20131057","journal-title":"Psychol Sci"},{"key":"9368_CR22","unstructured":"Forbes-Riley K, Litman DJ (2004) Predicting emotion in spoken dialogue from multiple knowledge sources. In: Proceedings of human language technology conference, North American chapter of the association computational linguistics (HLT\/NAACL), pp 201\u2013208"},{"key":"9368_CR23","doi-asserted-by":"crossref","unstructured":"France DJ, Shivavi RG, Silverman S, Silverman M, Wilkes M (2000) Acoustical properties of speech as indicators of depression and suicidal risk. IEEE Trans Biomed Eng, 7:829\u2013837","DOI":"10.1109\/10.846676"},{"key":"9368_CR24","doi-asserted-by":"crossref","unstructured":"Fu L, Mao X, Chen L (2008a) Relative speech emotion recognition based artificial neural network. In: Proceedings of IEEE Pacific-Asia workshop on computational intelligence and industrial application, pp 140\u2013144","DOI":"10.1109\/PACIIA.2008.355"},{"key":"9368_CR25","doi-asserted-by":"crossref","unstructured":"Fu L, Mao X, Chen L (2008b) Speaker independent emotion recognition using HMMs fusion system with relative features. In: Proceedings of 1st international conference on intelligent networks and intelligent systems, pp 608\u2013611","DOI":"10.1109\/ICINIS.2008.64"},{"key":"9368_CR26","doi-asserted-by":"crossref","unstructured":"Giannakopoulos T, Pikrakis A, Theodoridis S (2009) A dimensional approach to emotion recognition of speech from movies. In: Proceedings of IEEE international conference on acoustics, speech and signal processing, pp 65\u201368","DOI":"10.1109\/ICASSP.2009.4959521"},{"key":"9368_CR27","doi-asserted-by":"crossref","unstructured":"Graciarena M, Shriberg E, Stolcke A, Enos F, Hirschberg J, Kajarekar S (2006) Combining prosodic lexical and cepstral systems for deceptive speech detection. In: Proceedings of IEEE international conference on acoustics, speech and signal processing, pp 1033\u20131036","DOI":"10.1109\/ICASSP.2006.1660200"},{"key":"9368_CR28","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/MSP.2006.1621452","volume":"23","author":"A Hanjalic","year":"2006","unstructured":"Hanjalic A (2006) Extracting moods from pictures and sounds: towards truly personalized TV. IEEE Signal Process Mag 23: 90\u2013100","journal-title":"IEEE Signal Process Mag"},{"key":"9368_CR29","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1109\/TMM.2004.840618","volume":"7","author":"A Hanjalic","year":"2005","unstructured":"Hanjalic A, Xu LQ (2005) Affective video content representation and modeling. IEEE Trans Multimed 7: 143\u2013154","journal-title":"IEEE Trans Multimed"},{"key":"9368_CR30","unstructured":"Hoch S, Althoff F, McGlaun G, Rigoll G (2005) Bimodal fusion of emotional data in an automotive environment. In: Proceedings of international conference audio. Speech and Signal Processing, vol 2, pp 1085\u20131088"},{"key":"9368_CR31","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1023\/A:1023426522496","volume":"6","author":"V Hozjan","year":"2006","unstructured":"Hozjan V, Kacic Z (2006) Context-independent multilingual emotion recognition from speech signals. Int J Speech Technol 6: 311\u2013320","journal-title":"Int J Speech Technol"},{"key":"9368_CR32","doi-asserted-by":"crossref","unstructured":"Ijima Y, Tachibana M, Nose T, Kobayashi T (2009) Emotional speech recognition based on style estimation and adaptation with multiple-regression HMM. In: Proceedings of 2009 IEEE international conference on acoustics, speech and signal processing, pp 4157\u20134160","DOI":"10.1109\/ICASSP.2009.4960544"},{"key":"9368_CR33","doi-asserted-by":"crossref","unstructured":"Iliou T, Anagnostopoulos C-N (2009) Comparison of different classifiers for emotion recognition. In: Proceedings of panhellenic conference in informatics, pp 102\u2013106","DOI":"10.1109\/PCI.2009.7"},{"key":"9368_CR34","doi-asserted-by":"crossref","unstructured":"Jin Y, Zhao Y, Huang C, Zhao L (2009) Study on the emotion recognition of whispered speech. In: Proceedings of global congress on intelligent systems, pp 242\u2013246","DOI":"10.1109\/GCIS.2009.175"},{"key":"9368_CR35","doi-asserted-by":"crossref","unstructured":"Kockmann M, Burget L, Cernocky J (2009) Brno university of technology system for interspeech 2009 emotion challenge. In: Proceedings of INTERSPEECH, pp 348\u2013351","DOI":"10.21437\/Interspeech.2009-112"},{"key":"9368_CR36","unstructured":"Kostoulas TP, Fakotakis N (2006) A speaker dependent emotion recognition framework, CSNDSP. In: Proceedings of 5th international symposium computers, systems, networks and digital signal processing, pp 305\u2013309"},{"key":"9368_CR37","doi-asserted-by":"crossref","unstructured":"Kostoulas T, Ganchev T, Mporas I, Fakotakis N (2007) Detection of negative emotional states in real-world scenario. In: Proceedings of 19th IEEE international conference on tools with artificial intelligence, pp 502\u2013509","DOI":"10.1109\/ICTAI.2007.106"},{"key":"9368_CR38","doi-asserted-by":"crossref","unstructured":"Kostoulas T, Ganchev T, Lazaridis A, Fakotakis N (2010) Enhancing Emotion recognition from speech through feature selection. In: Sojka P, Hor\u00e1k A, Kopecek I, Pala K (eds) Text, speech and dialogue, lecture notes in artificial intelligence, vol 6231, pp 338\u2013344","DOI":"10.1007\/978-3-642-15760-8_43"},{"key":"9368_CR39","doi-asserted-by":"crossref","unstructured":"Kwon OW, Chan K, Hao J, Lee TW (2003) Emotion recognition by speech signals. In: Proceedings of Eurospeech conference, pp 125\u2013128","DOI":"10.21437\/Eurospeech.2003-80"},{"key":"9368_CR40","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/TSA.2004.838534","volume":"13","author":"CM Lee","year":"2005","unstructured":"Lee CM, Narayanan SS (2005) Toward detecting emotions in spoken dialogs. IEEE Trans Speech Audio Process 13: 293\u2013303","journal-title":"IEEE Trans Speech Audio Process"},{"key":"9368_CR41","doi-asserted-by":"crossref","unstructured":"Lee CM, Narayanan SS, Pieraccini R (2002) Combining acoustic and language information for emotion recognition. In: Proceedings of interspeech, pp 873\u2013376","DOI":"10.21437\/ICSLP.2002-296"},{"key":"9368_CR42","doi-asserted-by":"crossref","unstructured":"Lee CM, Yildirim S, Bulut M, Kazemzadeh A, Busso C, Deng Z, Lee SS, Narayanan S (2004) Emotion recognition based on phoneme classes. In: Proceedings of international conference spoken language processing, pp 205\u2013211","DOI":"10.21437\/Interspeech.2004-322"},{"key":"9368_CR43","doi-asserted-by":"crossref","unstructured":"Lee C, Mower E, Busso C, Lee S, Narayanan S (2009) Emotion recognition using a hierarchical binary decision tree approach. In: Proceedings of INTERSPEECH, pp 320\u2013323","DOI":"10.21437\/Interspeech.2009-105"},{"key":"9368_CR44","doi-asserted-by":"crossref","unstructured":"Litman DJ, Forbes-Riley K (2004) Predicting student emotions in computer-human tutoring dialogues In: Proceedings of 42nd annual meeting on association for computational linguistics","DOI":"10.3115\/1218955.1219000"},{"key":"9368_CR45","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1109\/TMM.2010.2051872","volume":"12","author":"I Luengo","year":"2010","unstructured":"Luengo I, Navas E, Hernaez I (2010) Feature analysis and evaluation for automatic emotion identification in speech. IEEE Trans Multimed 12: 490\u2013501","journal-title":"IEEE Trans Multimed"},{"key":"9368_CR46","unstructured":"Lugger M, Yang B (2007a) An incremental analysis of different feature groups in speaker independent emotion recognition. In: Proceedings of international congress phonetic sciences, pp 2149\u20132152"},{"key":"9368_CR47","doi-asserted-by":"crossref","unstructured":"Lugger M, Yang B (2007b) The relevance of voice quality features in speaker independent emotion recognition. In: Proceedings of IEEE international conference on acoustics, speech and signal processing, pp 17\u201320","DOI":"10.1109\/ICASSP.2007.367152"},{"key":"9368_CR48","unstructured":"Manning CD, Sch\u00fctze H (1999) Foundations of statistical natural language processing. MIT Press, Cambridge"},{"key":"9368_CR49","doi-asserted-by":"crossref","unstructured":"Mao X, Chen L, Fu L (2009) Multi-level speech emotion recognition based on HMM and ANN. In: Proceedings of world congress on computer science and information engineering, pp 225\u2013229","DOI":"10.1109\/CSIE.2009.113"},{"key":"9368_CR50","doi-asserted-by":"crossref","first-page":"1078","DOI":"10.1109\/TBME.2006.873548","volume":"53","author":"S Matos","year":"2006","unstructured":"Matos S, Birring SS, Pavord ID, Evans DH (2006) Detection of cough signals in continuous audio recordings Using HMM. IEEE Trans Biomed Eng 53: 1078\u20131083","journal-title":"IEEE Trans Biomed Eng"},{"key":"9368_CR51","unstructured":"Mishra HK, Sekhar CC (2009) Variational gaussian mixture models for speech emotion recognition. In: Proceedings of 7th international conference on advances in pattern recognition, pp 183\u2013186"},{"key":"9368_CR52","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.specom.2006.11.004","volume":"49","author":"D Morrison","year":"2007","unstructured":"Morrison D, Wang R, Silva LCD (2007) Ensemble methods for spoken emotion recognition in call-centres. Speech Commun 49: 98\u2013112","journal-title":"Speech Commun"},{"key":"9368_CR53","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1109\/TASL.2006.876121","volume":"14","author":"E Navas","year":"2006","unstructured":"Navas E, Hern\u00e1ez I, Luengo I (2006) An objective and subjective study of the role of semantics and prosodic features in building corpora for emotional TTS. IEEE Trans Audio Speech Lang Process 14: 1117\u20131127","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"9368_CR54","doi-asserted-by":"crossref","unstructured":"Neiberg D, Elenius K, Laskowski K (2006) Emotion recognition in spontaneous speech using GMMs. In: Proceedings of INTERSPEECH conference, pp 809\u2013812","DOI":"10.21437\/Interspeech.2006-277"},{"key":"9368_CR55","doi-asserted-by":"crossref","unstructured":"Nogueiras A, Moreno A, Bonafonte A, Mari\u00f1o JB (2001) Speech emotion recognition using Hidden Markov models. In: Proceedings of EUROSPEECH, pp 2679\u20132682","DOI":"10.21437\/Eurospeech.2001-627"},{"key":"9368_CR56","unstructured":"Nwe TL, Foo SW, De Silva LC (2003) Classification of stress in speech using linear and nonlinear features. In: Proceedings of IEEE international conference acoustics, speech, and signal processing, pp 9\u201312"},{"key":"9368_CR57","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511571299","volume-title":"The cognitive structure of emotions","author":"A Ortony","year":"1988","unstructured":"Ortony A, Clore G, Collins A (1988) The cognitive structure of emotions. Cambridge University Press, Cambridge"},{"key":"9368_CR58","doi-asserted-by":"crossref","unstructured":"Pal P, Iyer AN, Yantorno RE (2006) Emotion detection from infant facial expressions and cries. In: Proceedings of IEEE international conference on acoustics, speech, and signal processing, pp 721\u2013724","DOI":"10.1109\/ICASSP.2006.1660444"},{"key":"9368_CR59","doi-asserted-by":"crossref","unstructured":"Pao TL, Liao WY, Chen YT, Yeh JH, Cheng YM, Chien CS (2007a) Comparison of several classifiers for emotion recognition from noisy mandarin speech. In: Proceedings of 3rd international conference on international information hiding and multimedia signal processing, pp 23\u201326","DOI":"10.1109\/IIHMSP.2007.4457484"},{"key":"9368_CR60","doi-asserted-by":"crossref","unstructured":"Pao TL, Chien CS, Chen YT, Yeh JH, Cheng YM, Liao WY (2007b) Combination of multiple classifiers for improving emotion recognition in Mandarin speech. In: Proceedings of 3rd international conference on international information hiding and multimedia signal processing, pp 35\u201338","DOI":"10.1109\/IIHMSP.2007.4457487"},{"key":"9368_CR61","doi-asserted-by":"crossref","unstructured":"Petridis S, Pantic M (2008) Audiovisual discrimination between laughter and speech. In: Proceedings of IEEE international conference on acoustics, speech, and signal processing, pp 5117\u20135120","DOI":"10.1109\/ICASSP.2008.4518810"},{"key":"9368_CR62","doi-asserted-by":"crossref","unstructured":"Rong J, Chen YPP, Chowdhury M, Li G (2007) Acoustic features extraction for emotion recognition. In: Proceedings 6th IEEE\/ACIS international conference on computer and information science, pp 419\u2013424","DOI":"10.1109\/ICIS.2007.48"},{"key":"9368_CR63","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1037\/0022-3514.57.3.493","volume":"57","author":"JA Russell","year":"1989","unstructured":"Russell JA, Weiss A, Mendelsohn GA (1989) Affect Grid: a single-item scale of pleasure and arousal. J Pers Soc Psychol 57: 493\u2013502","journal-title":"J Pers Soc Psychol"},{"key":"9368_CR64","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1146\/annurev.psych.54.101601.145102","volume":"54","author":"JA Russell","year":"2003","unstructured":"Russell JA, Bachorowski J, Fernandez-Dols J (2003) Facial and vocal expressions of emotion. Annu Revis Psychol 54: 329\u2013349","journal-title":"Annu Revis Psychol"},{"key":"9368_CR65","doi-asserted-by":"crossref","unstructured":"Schroder M (2003) Experimental study of affect bursts. Speech Commun 40:99\u2013116","DOI":"10.1016\/S0167-6393(02)00078-X"},{"key":"9368_CR66","doi-asserted-by":"crossref","unstructured":"Schuller B, Rigoll G (2009) Recognising interest in conversational speech\u2013comparing bag of frames and supra-segmental features. In: Proceedings of INTERSPEECH, pp 1999\u20132002","DOI":"10.21437\/Interspeech.2009-484"},{"key":"9368_CR67","unstructured":"Schuller B, Rigoll G, Lang M (2003) Hidden Markov model-based speech emotion recognition. In: Proceedings of international conference on multimedia and expo, pp 401\u2013404"},{"key":"9368_CR68","doi-asserted-by":"crossref","unstructured":"Schuller B, Rigoll G, Lang M (2004) Speech emotion recognition combining acoustic features and linguistic information in a hybrid support vector machine-belief network architecture. In: Proceedings of IEEE international conference acoustics, speech, and signal processing, pp. 577\u2013580","DOI":"10.1109\/ICASSP.2004.1326051"},{"key":"9368_CR69","doi-asserted-by":"crossref","unstructured":"Schuller B, Muller R, Lang M, Rigoll G (2005a) Speaker independent emotion recognition by early fusion of acoustic and linguistic features within ensembles. In: Proceedings of 9th Eurospeech\u2013Interspeech, pp 805\u2013809","DOI":"10.21437\/Interspeech.2005-379"},{"key":"9368_CR70","doi-asserted-by":"crossref","unstructured":"Schuller B, Villar RJ, Rigoll G, Lang M (2005b) Meta-classifiers in acoustic and linguistic feature fusion-based affect recognition. In: Proceedings of IEEE international conference on acoustics, speech and signal processing, pp 325\u2013328","DOI":"10.1109\/ICASSP.2005.1415116"},{"key":"9368_CR71","doi-asserted-by":"crossref","unstructured":"Schuller B, Reiter S, Mueller R, Al-Hames M, Lang M, Rigoll G (2005c) Speaker-independent speech emotion recognition by ensemble classification. In: Proceedings international conference on multimedia and expo, pp 864\u2013867","DOI":"10.1109\/ICME.2005.1521560"},{"key":"9368_CR72","doi-asserted-by":"crossref","unstructured":"Schuller B, Reiter S, Rigoll G (2006) Evolutionary feature generation in speech emotion recognition. In: Proceedings 2006 IEEE international conference on multimedia and expo, pp 5\u20138","DOI":"10.1109\/ICME.2006.262500"},{"key":"9368_CR73","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, Aharonson V (2007) The relevance of feature type for the automatic classification of emotional user states: low level descriptors and functionals. In: Proceedings of INTERSPEECH, pp 2253\u20132256","DOI":"10.21437\/Interspeech.2007-612"},{"key":"9368_CR74","doi-asserted-by":"crossref","first-page":"1760","DOI":"10.1016\/j.imavis.2009.02.013","volume":"27","author":"B Schuller","year":"2009","unstructured":"Schuller B, M\u00fcller R, Eyben F, Gast J, H\u00f6rnler B, W\u00f6llmer M, Rigoll G, H\u00f6thker A, Konosu H (2009) Being bored? Recognising natural interest by extensive audiovisual integration for real-life application. Image Vis Comput 27: 1760\u20131774","journal-title":"Image Vis Comput"},{"key":"9368_CR75","volume-title":"The role of prosody in affective speech","author":"B Schuller","year":"2009","unstructured":"Schuller B, Wollmer M, Eyben F, Rigoll G (2009) The role of prosody in affective speech. Peter Lan Publishing Group, Bern"},{"key":"9368_CR76","doi-asserted-by":"crossref","unstructured":"Schuller B, Batliner A, Steidl S, Seppi D (2009c) Emotion recognition from speech: putting ASR in the loop. In: Proceedings of IEEE international conference on acoustics, speech and signal processing, pp 4585\u20134588","DOI":"10.1109\/ICASSP.2009.4960651"},{"key":"9368_CR77","doi-asserted-by":"crossref","unstructured":"Schuller B, Schenk J, Rigoll G, Knaup T (2009d) \u201cThe Godfather\u201d vs. \u201cChaos\u201d: comparing linguistic analysis based on on-line knowledge sources and bags-of-n-grams for movie review valence estimation. In: Proceedings of 10th international conference on document analysis and recognition, pp 858-862","DOI":"10.1109\/ICDAR.2009.194"},{"key":"9368_CR78","doi-asserted-by":"crossref","unstructured":"Schuller B, Steidl S, Batliner A (2009e) The INTERSPEECH 2009 emotion challenge. In: Proceedings of INTERSPEECH, pp 312\u2013315","DOI":"10.21437\/Interspeech.2009-103"},{"key":"9368_CR79","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1109\/T-AFFC.2010.8","volume":"1","author":"B Schuller","year":"2010","unstructured":"Schuller B, Vlasenko B, Eyben F, Wollmer M, Stuhlsatz A, Wendemuth A, Rigoll G (2010) Cross-corpus acoustic emotion recognition: variances and strategies. IEEE Trans Affect Comput 1: 119\u2013131","journal-title":"IEEE Trans Affect Comput"},{"key":"9368_CR80","doi-asserted-by":"crossref","first-page":"1062","DOI":"10.1016\/j.specom.2011.01.011","volume":"53","author":"B Schuller","year":"2011","unstructured":"Schuller B, Batliner A, Steidl S, Seppi D (2011) Recognising realistic emotions and affect in speech: state of the art and lessons learnt from the first challenge. Speech Commun 53: 1062\u20131087","journal-title":"Speech Commun"},{"key":"9368_CR81","unstructured":"Shami MT, Kamel MS (2005) Segment-based approach to the recognition of emotions in speech. In: Proceedings of IEEE international conference on multimedia and expo, pp 4\u20137"},{"key":"9368_CR82","doi-asserted-by":"crossref","unstructured":"Stuhlsatz A, Meyer C, Eyben F, Zielke T, Meier G, Schuller B (2011) Deep neural networks for acoustic emotion recognition: raising the benchmarks. In: Proceedings international conference on acoustics speech and signal processing, pp 5688\u20135691","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"9368_CR83","unstructured":"Sidorova J (2007) Speech emotion recognition. Ph.D. Thesis, Universitat Pompeu Fabra, Barcelona"},{"key":"9368_CR84","doi-asserted-by":"crossref","unstructured":"Vlasenko B, Schuller B, Wendemut A, Rigoll G, Frame vs (2007) Turn-level: emotion recognition from speech considering static and dynamic processing. In: Proceedings 2nd international conference on affective computing and intelligent interaction, pp 139\u2013147","DOI":"10.1007\/978-3-540-74889-2_13"},{"key":"9368_CR85","doi-asserted-by":"crossref","unstructured":"Vogt T, Andr\u00e9 E (2005) Comparing feature sets for acted and spontaneous speech in view of automatic emotion recognition. In: Proceedings IEEE international conference on multimedia and expo, pp 474\u2013477","DOI":"10.1109\/ICME.2005.1521463"},{"key":"9368_CR86","unstructured":"Vogt T, Andr\u00e9 E (2006) Improving automatic emotion recognition from speech via gender differentiation. In: Proceedings of language resources and evaluation conference, pp 1123\u20131126"},{"key":"9368_CR87","doi-asserted-by":"crossref","unstructured":"Vogt T, Andr\u00e9 E (2009) Exploring the benefits of discretization of acoustic features for speech emotion recognition. In: Proceedings 10th INTERSPEECH conference, pp 328\u2013331","DOI":"10.21437\/Interspeech.2009-107"},{"key":"9368_CR88","doi-asserted-by":"crossref","unstructured":"Wagner J, Kim NJ, Andre E (2005) From physiological signals to emotions: implementing and comparing selected methods for feature extraction and classification. In: Proceedings of IEEE international conference multimedia and expo, pp 940\u2013943","DOI":"10.1109\/ICME.2005.1521579"},{"key":"9368_CR89","doi-asserted-by":"crossref","unstructured":"Wang Y, Du S, Zhan Y (2008) Adaptive and optimal classification of speech emotion recognition. In: Proceedings of 4th international conference on natural computation, pp 407\u2013411","DOI":"10.1109\/ICNC.2008.713"},{"key":"9368_CR90","doi-asserted-by":"crossref","unstructured":"Wang S, Ling X, Zhang F, Tong J (2010) Speech emotion recognition based on principal component analysis and back propagation neural network. In: Proceedings of international conference on measuring technology and mechatronics automation, pp 437\u2013440","DOI":"10.1109\/ICMTMA.2010.523"},{"key":"9368_CR91","doi-asserted-by":"crossref","unstructured":"Wenjing H, Haifeng L, Chunyu G (2009) A hybrid speech emotion perception method of VQ-based feature processing and ANN recognition. In: Proceedings of global congress on intelligent systems, pp 145\u2013149","DOI":"10.1109\/GCIS.2009.432"},{"key":"9368_CR92","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511521256","volume-title":"Emotions across languages and cultures: diversity and universals","author":"A Wierzbicka","year":"1999","unstructured":"Wierzbicka A (1999) Emotions across languages and cultures: diversity and universals. Cambridge University Press, Cambridge"},{"key":"9368_CR93","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1109\/T-AFFC.2010.16","volume":"2","author":"CH Wu","year":"2011","unstructured":"Wu CH, Liang WB (2011) Emotion recognition of affective speech based on multiple classifiers using acoustic-prosodic information and semantic labels. IEEE Trans Affect Comput 2: 10\u201321","journal-title":"IEEE Trans Affect Comput"},{"key":"9368_CR94","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1145\/1165255.1165259","volume":"5","author":"CH Wu","year":"2006","unstructured":"Wu CH, Chuang ZJ, Lin YC (2006) Emotion recognition from text using semantic label and separable mixture model. ACM Trans Asian Lang Inf Process 5: 165\u2013182","journal-title":"ACM Trans Asian Lang Inf Process"},{"key":"9368_CR95","doi-asserted-by":"crossref","unstructured":"Wu S, Falk TH, Chan WY (2009) Automatic recognition of speech emotion using long-term spectro-temporal features. In: Proceedings of 16th international conference on digital signal processing","DOI":"10.1109\/ICDSP.2009.5201047"},{"key":"9368_CR96","doi-asserted-by":"crossref","unstructured":"Yang C, Ji L, Liu G (2009a) Study to speech emotion recognition based on TWINsSVM. In: Proceedings of 5th international conference on natural computation, pp 312\u2013316","DOI":"10.1109\/ICNC.2009.464"},{"key":"9368_CR97","doi-asserted-by":"crossref","unstructured":"Yang T, Yang J, Bi F (2009b) Emotion statuses recognition of speech signal using intuitionistic fuzzy set. In: Proceedings of world congress on software engineering, pp 204\u2013207","DOI":"10.1109\/WCSE.2009.237"},{"key":"9368_CR98","unstructured":"You M, Chen C, Bu J, Liu J, Tao J (2006) Emotional speech analysis on nonlinear manifold. In: Proceedings of 18th international conference on pattern recognition, pp 91\u201394"},{"key":"9368_CR99","doi-asserted-by":"crossref","unstructured":"Yu W (2008) Research and implementation of emotional feature classification and recognition in speech signal. In: Proceedings of international symposium on intelligent information technology application, pp 471\u2013474","DOI":"10.1109\/IITA.Workshops.2008.219"},{"key":"9368_CR100","doi-asserted-by":"crossref","unstructured":"Yun S, Yoo CD, (2009) Speech emotion recognition via a max-margin framework incorporating a loss function based on the Watson and Tellegen\u2019s emotion model. In: Proceedings IEEE international conference on acoustics, speech and signal processing, pp 4169\u20134172","DOI":"10.1109\/ICASSP.2009.4960547"},{"key":"9368_CR101","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: 39\u201358","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9368_CR102","doi-asserted-by":"crossref","unstructured":"Zhou Y, Zhang J, Wang L, Yan Y (2009a) Emotion recognition and conversion for mandarin speech. In: Proceedings of 6th international conference on fuzzy systems and knowledge discovery, pp 179\u2013183","DOI":"10.1109\/FSKD.2009.474"},{"key":"9368_CR103","doi-asserted-by":"crossref","unstructured":"Zhou Y, Sun Y, Yang L, Yan Y (2009b) Applying articulatory features to speech emotion recognition. In: Proceedings of international conference on research challenges in computer science, pp 73\u201376","DOI":"10.1109\/ICRCCS.2009.26"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-012-9368-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-012-9368-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-012-9368-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,20]],"date-time":"2025-04-20T12:26:36Z","timestamp":1745151996000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-012-9368-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11,9]]},"references-count":103,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2015,2]]}},"alternative-id":["9368"],"URL":"https:\/\/doi.org\/10.1007\/s10462-012-9368-5","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,11,9]]}}}