{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:15:18Z","timestamp":1760955318362},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2012,2,15]],"date-time":"2012-02-15T00:00:00Z","timestamp":1329264000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1007\/s00521-012-0884-7","type":"journal-article","created":{"date-parts":[[2012,2,14]],"date-time":"2012-02-14T05:35:59Z","timestamp":1329197759000},"page":"1181-1191","source":"Crossref","is-referenced-by-count":17,"title":["Emotion recognition improvement using normalized formant supplementary features by hybrid of DTW-MLP-GMM model"],"prefix":"10.1007","volume":"22","author":[{"given":"Davood","family":"Gharavian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mansour","family":"Sheikhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farhad","family":"Ashoftedel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,2,15]]},"reference":[{"key":"884_CR1","doi-asserted-by":"crossref","first-page":"1415","DOI":"10.1016\/j.sigpro.2009.09.009","volume":"90","author":"B Yang","year":"2010","unstructured":"Yang B, Lugger M (2010) Emotion recognition from speech signals using new harmony features. Signal Process 90:1415\u20131423","journal-title":"Signal Process"},{"key":"884_CR2","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":"884_CR3","doi-asserted-by":"crossref","unstructured":"Dellaert F, Polzin T, Waibel A (1996) Recognizing emotion in speech. In: The proceedings of international conference on spoken language processing, vol 3, pp 1970\u20131973","DOI":"10.1109\/ICSLP.1996.608022"},{"key":"884_CR4","doi-asserted-by":"crossref","unstructured":"Ai H, Litman DJ, Forbes-Riley K, Rotaru M, Tetreault J, Purandare A (2006) Using system and user performance features to improve emotion detection in spoken tutoring systems. In: The proceedings of Interspeech, pp 797\u2013800","DOI":"10.21437\/Interspeech.2006-274"},{"key":"884_CR5","doi-asserted-by":"crossref","unstructured":"Devillers L, Vidrascu L (2006) Real-life emotions detection with lexical and paralinguistic cues on human\u2013human call center dialogs. In: The proceedings of Interspeech, pp 801\u2013804","DOI":"10.21437\/Interspeech.2006-275"},{"key":"884_CR6","doi-asserted-by":"crossref","unstructured":"Polzehl T, Sundaram S, Ketabdar H, Wagner M, Metze F (2009) Emotion classification in children\u2019s speech using fusion of acoustic and linguistic features. In: The proceedings of Interspeech, pp 340\u2013343","DOI":"10.21437\/Interspeech.2009-110"},{"key":"884_CR7","doi-asserted-by":"crossref","first-page":"1210","DOI":"10.1016\/j.specom.2011.01.006","volume":"53","author":"R L\u00f3pez-C\u00f3zar","year":"2011","unstructured":"L\u00f3pez-C\u00f3zar R, Silovsky J, Kroul M (2011) Enhancement of emotion detection in spoken dialogue systems by combining several information sources. Speech Commun 53:1210\u20131228","journal-title":"Speech Commun"},{"key":"884_CR8","doi-asserted-by":"crossref","first-page":"1088","DOI":"10.1016\/j.specom.2011.05.003","volume":"53","author":"R Fernandez","year":"2011","unstructured":"Fernandez R, Picard R (2011) Recognizing affect from speech prosody using hierarchical graphical models. Speech Commun 53:1088\u20131103","journal-title":"Speech Commun"},{"key":"884_CR9","doi-asserted-by":"crossref","unstructured":"Kao Y, Lee L (2006) Feature analysis for emotion recognition from Mandarin speech considering the special characteristics of Chinese language. In: The proceedings of international conference on spoken language processing, pp 1814\u20131817","DOI":"10.21437\/Interspeech.2006-501"},{"key":"884_CR10","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1016\/j.specom.2006.04.003","volume":"48","author":"D Ververidis","year":"2006","unstructured":"Ververidis D, Kotropoulos C (2006) Emotional speech recognition: resources, features, and methods. Speech Commun 48:1162\u20131181","journal-title":"Speech Commun"},{"key":"884_CR11","first-page":"1695","volume":"4","author":"T Pao","year":"2008","unstructured":"Pao T, Chen Y, Yeh J, Chang Y (2008) Emotion recognition and evaluation of Mandarin speech using weighted D-KNN classification. Int J Innov Comput Inf Control 4:1695\u20131709","journal-title":"Int J Innov Comput Inf Control"},{"key":"884_CR12","doi-asserted-by":"crossref","first-page":"8197","DOI":"10.1016\/j.eswa.2008.10.005","volume":"36","author":"H Altun","year":"2009","unstructured":"Altun H, Polat G (2009) Boosting selection of speech related features to improve performance of multi-class SVMs in emotion detection. Expert Syst Appl 36:8197\u20138203","journal-title":"Expert Syst Appl"},{"key":"884_CR13","unstructured":"Gaj\u0161ek R, Struc V, Miheli\u010d F (2010) Multi-modal emotion recognition using canonical correlations and acoustic features. In: The proceedings of international conference on pattern recognition, pp 4133\u20134136"},{"key":"884_CR14","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1016\/j.specom.2010.02.010","volume":"52","author":"D Bitouk","year":"2010","unstructured":"Bitouk D, Verma R, Nenkova A (2010) Class-level spectral features for emotion recognition. Speech Commun 52:613\u2013625","journal-title":"Speech Commun"},{"key":"884_CR15","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1016\/j.chb.2010.10.027","volume":"27","author":"J Yeh","year":"2010","unstructured":"Yeh J, Pao T, Lin C, Tsai Y, Chen Y (2010) Segment-based emotion recognition from continuous Mandarin Chinese speech. Comput Hum Behav 27:1545\u20131552","journal-title":"Comput Hum Behav"},{"key":"884_CR16","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1016\/j.specom.2010.08.013","volume":"53","author":"S Wu","year":"2011","unstructured":"Wu S, Falk TH, Chan W-Y (2011) Automatic speech emotion recognition using modulation spectral features. Speech Commun 53:768\u2013785","journal-title":"Speech Commun"},{"key":"884_CR17","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.bspc.2010.11.001","volume":"6","author":"L He","year":"2011","unstructured":"He L, Lech M, Maddage NC, Allen NB (2011) Study of empirical mode decomposition and spectral analysis for stress and emotion classification in natural speech. Biomed Signal Process Control 6:139\u2013146","journal-title":"Biomed Signal Process Control"},{"key":"884_CR18","doi-asserted-by":"crossref","first-page":"1198","DOI":"10.1016\/j.specom.2011.05.002","volume":"53","author":"T Polzehl","year":"2011","unstructured":"Polzehl T, Schmitt A, Metze F, Wagner M (2011) Anger recognition in speech using acoustic and linguistic cues. Speech Commun 53:1198\u20131209","journal-title":"Speech Commun"},{"key":"884_CR19","unstructured":"Ververidis D, Kotropoulos C (2006) Fast sequential floating forward selection applied to emotional speech features estimated on DES and SUSAS data collections. In: The proceedings of European signal processing conference, pp 1\u20135"},{"key":"884_CR20","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1016\/j.csl.2009.12.003","volume":"25","author":"A Batliner","year":"2011","unstructured":"Batliner A, Steidl S, Schuller B, Seppi D, Vogt T, Wagner J, Devillers L, Vidrascu L, Aharonson V, Kessous L, Amir N (2011) Whodunnit-searching for the most important feature types signalling emotion-related user states in speech. Comput Speech Lang 25:4\u201328","journal-title":"Comput Speech Lang"},{"key":"884_CR21","unstructured":"Haq S, Jackson PJB, Edge J (2008) Audio-visual feature selection and reduction for emotion classification. In: The proceedings of international conference on auditory-visual speech processing, pp 185\u2013190"},{"key":"884_CR22","doi-asserted-by":"crossref","unstructured":"Gharavian D, Sheikhan M, Nazerieh AR, Garoucy S (2011) Speech emotion recognition using FCBF feature selection method and GA-optimized fuzzy ARTMAP neural network. Neural Comput Appl [Published Online 27 May 2011 (doi: 10.1007\/s00521-011-0643-1 )]","DOI":"10.1007\/s00521-011-0643-1"},{"key":"884_CR23","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1016\/j.ipm.2008.09.003","volume":"45","author":"J Rong","year":"2009","unstructured":"Rong J, Li G, Chen YP (2009) Acoustic feature selection for automatic emotion recognition from speech. Inf Process Manag 45:315\u2013328","journal-title":"Inf Process Manag"},{"key":"884_CR24","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1016\/j.csl.2009.02.005","volume":"24","author":"AI Iliev","year":"2010","unstructured":"Iliev AI, Scordilis MS, Papa JP, Falc\u00e3o AX (2010) Spoken emotion recognition through optimum-path forest classification using glottal features. Comput Speech Lang 24:445\u2013460","journal-title":"Comput Speech Lang"},{"key":"884_CR25","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1016\/j.specom.2010.09.007","volume":"53","author":"E V\u00e4yrynen","year":"2011","unstructured":"V\u00e4yrynen E, Toivanen J, Sepp\u00e4nen T (2011) Classification of emotion in spoken Finnish using vowel-length segments: increasing reliability with a fusion technique. Speech Commun 53:269\u2013282","journal-title":"Speech Commun"},{"key":"884_CR26","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.specom.2011.06.001","volume":"54","author":"E Fersini","year":"2012","unstructured":"Fersini E, Messina E, Archetti F (2012) Emotional states in judicial courtrooms: an experimental investigation. Speech Commun 54:11\u201322","journal-title":"Speech Commun"},{"key":"884_CR27","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M El Ayadi","year":"2011","unstructured":"El Ayadi M, Kamel MS, Karray F (2011) Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recogn 44:572\u2013587","journal-title":"Pattern Recogn"},{"key":"884_CR28","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1016\/j.csl.2010.10.001","volume":"25","author":"EM Albornoz","year":"2011","unstructured":"Albornoz EM, Milone DH, Rufiner HL (2011) Spoken emotion recognition using hierarchical classifiers. Comput Speech Lang 25:556\u2013570","journal-title":"Comput Speech Lang"},{"key":"884_CR29","doi-asserted-by":"crossref","unstructured":"Kockmann M, Burget L, \u010cernocky JH (2011) Application of speaker- and language identification state-of-the-art techniques for emotion recognition. Speech Commun (Article in Press, doi: 10.1016\/j.specom.2011.01.007 )","DOI":"10.1016\/j.specom.2011.01.007"},{"key":"884_CR30","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1016\/j.measurement.2008.10.005","volume":"42","author":"S Chandaka","year":"2009","unstructured":"Chandaka S, Chatterjee A, Munshi S (2009) Support vector machines employing cross-correlation for emotional speech recognition. Measurement 42:611\u2013618","journal-title":"Measurement"},{"key":"884_CR31","doi-asserted-by":"crossref","unstructured":"Yacoub S, Simske S, Lin X, Burns J (2003) Recognition of emotions in interactive voice response systems. In: The proceeding of European conference on speech communication and technology, pp 729\u2013732","DOI":"10.21437\/Eurospeech.2003-307"},{"key":"884_CR32","doi-asserted-by":"crossref","unstructured":"Lee CM, Narayanan S, Pieraccini R (2002) Combining acoustic and language information for emotion recognition. In: The proceedings of the international conference on spoken language processing, pp 873\u2013876","DOI":"10.21437\/ICSLP.2002-296"},{"key":"884_CR33","unstructured":"Park CH, Lee DW, Sim KB (2002) Emotion recognition of speech based on RNN. In: The proceedings of the international conference on machine learning and cybernetics, vol 4, pp 2210\u20132213"},{"key":"884_CR34","doi-asserted-by":"crossref","first-page":"2553","DOI":"10.1016\/j.neucom.2007.11.043","volume":"71","author":"G Caridakis","year":"2008","unstructured":"Caridakis G, Karpouzis K, Kollias S (2008) User and context adaptive neural networks for emotion recognition. Neurocomputing 71:2553\u20132562","journal-title":"Neurocomputing"},{"key":"884_CR35","unstructured":"Planet S, Iriondo I, Socor\u2032o J, Monzo C, Adell J (2009) GTMURL contribution to the INTERSPEECH 2009 emotion challenge. In: The proceedings of 10th annual of the international speech communication association (Interspeech\u201909), pp 316\u2013319"},{"key":"884_CR36","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1016\/j.specom.2011.06.004","volume":"53","author":"C\u2013C Lee","year":"2011","unstructured":"Lee C\u2013C, Mower E, Busso C, Lee S, Narayanan S (2011) Emotion recognition using a hierarchical binary decision tree approach. Speech Commun 53:1162\u20131171","journal-title":"Speech Commun"},{"key":"884_CR37","first-page":"1531","volume":"5","author":"F Fleuret","year":"2004","unstructured":"Fleuret F (2004) Fast binary feature selection with conditional mutual information. J Mach Learn Res 5:1531\u20131555","journal-title":"J Mach Learn Res"},{"key":"884_CR38","unstructured":"NIST\/SEMATECH (2011) e-Handbook of Statistical Methods. ( http:\/\/www.itl.nist.gov\/div898\/handbook\/ )"},{"key":"884_CR39","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/TASSP.1975.1162641","volume":"23","author":"F Itakura","year":"1975","unstructured":"Itakura F (1975) Minimum prediction residual principle applied to speech recognition. IEEE Trans Acoust Speech Signal Process 23:67\u201372","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"884_CR40","doi-asserted-by":"crossref","unstructured":"Yu F, Chang E, Xu Y, Shum H (2001) Emotion detection from speech to enrich multimedia content. In: The proceedings of the IEEE Pacific Rim conference on multimedia: advances in multimedia information processing, pp 550\u2013557","DOI":"10.1007\/3-540-45453-5_71"},{"key":"884_CR41","doi-asserted-by":"crossref","unstructured":"Kwon OW, Chan K, Hao J, Lee TW (2003) Emotion recognition by speech signal. In: The proceedings of the European conference on speech communication and technology, pp 125\u2013128","DOI":"10.21437\/Eurospeech.2003-80"},{"key":"884_CR42","unstructured":"Ayadi M, Kamel S, Karray F (2007) Speech emotion recognition using Gaussian mixture vector autoregressive models. In: The proceedings of the international conference on acoustics, speech, and signal processing, vol 5, pp 957\u2013960"},{"key":"884_CR43","unstructured":"Vlasenko B, Wendemuth A (2007) Tuning hidden Markov model for speech emotion recognition. In: The proceedings of 33rd German annual conference on acoustics, pp 317\u2013320"},{"key":"884_CR44","unstructured":"Sidorova J (2009) Speech emotion recognition with TGI\u00a0+\u00a0.2 classifier. In: The proceedings of the EACL student research workshop, pp 54\u201360"},{"key":"884_CR45","doi-asserted-by":"crossref","unstructured":"Petrushin VA (2000) Emotion recognition in speech signal: experimental study, development, and application. In: The proceedings of the international conference on spoken language processing, pp 222\u2013225","DOI":"10.21437\/ICSLP.2000-791"},{"key":"884_CR46","doi-asserted-by":"crossref","unstructured":"Luengo I, Navas E, Hern\u00e1ez I, Sanchez J (2005) Automatic emotion recognition using prosodic parameters. In: The proceeding of Interspeech, pp 493\u2013496","DOI":"10.21437\/Interspeech.2005-324"},{"key":"884_CR47","doi-asserted-by":"crossref","unstructured":"Neiberg D, Elenius K, Laskowski K (2006) Emotion recognition in spontaneous speech using GMMs. In: The proceedings of international conference on spoken language processing, pp 809\u2013812","DOI":"10.21437\/Interspeech.2006-277"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-012-0884-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-012-0884-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-012-0884-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T17:28:03Z","timestamp":1686763683000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-012-0884-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,2,15]]},"references-count":47,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2013,5]]}},"alternative-id":["884"],"URL":"https:\/\/doi.org\/10.1007\/s00521-012-0884-7","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,2,15]]}}}