{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T15:58:21Z","timestamp":1761580701435,"version":"3.37.0"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2009,7,9]],"date-time":"2009-07-09T00:00:00Z","timestamp":1247097600000},"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":[[2010,1]]},"DOI":"10.1007\/s11042-009-0319-3","type":"journal-article","created":{"date-parts":[[2009,7,8]],"date-time":"2009-07-08T06:50:00Z","timestamp":1247035800000},"page":"119-145","source":"Crossref","is-referenced-by-count":26,"title":["Multi-stage classification of emotional speech motivated by a dimensional emotion model"],"prefix":"10.1007","volume":"46","author":[{"given":"Zhongzhe","family":"Xiao","sequence":"first","affiliation":[]},{"given":"Emmanuel","family":"Dellandrea","sequence":"additional","affiliation":[]},{"given":"Weibei","family":"Dou","sequence":"additional","affiliation":[]},{"given":"Liming","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2009,7,9]]},"reference":[{"key":"319_CR1","unstructured":"Abelin A, Allwood J (2000) Cross-linguistic interpretation of emotional prosody. Proceedings of the ISCA Workshop on Speech and Emotion, Belfast"},{"issue":"3","key":"319_CR2","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1109\/TASSP.1976.1162800","volume":"24","author":"B Atal","year":"1976","unstructured":"Atal B, Rabiner L (1976) A pattern recognition approach to voiced-unvoiced-silence classification with applications to speech recognition. IEEE Transactions on ASSP 24(3):201\u2013212","journal-title":"IEEE Transactions on ASSP"},{"issue":"3","key":"319_CR3","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1037\/0022-3514.70.3.614","volume":"70","author":"R Banse","year":"1996","unstructured":"Banse R, Sherer KR (1996) Acoustic profiles in vocal emotion expression. J Pers Soc Psychol 70(3):614\u2013636. doi: 10.1037\/0022-3514.70.3.614","journal-title":"J Pers Soc Psychol"},{"key":"319_CR4","doi-asserted-by":"crossref","unstructured":"Bellman R (1961) Adaptive control processes: a guided tour, Princeton University Press","DOI":"10.1515\/9781400874668"},{"key":"319_CR5","unstructured":"Bishop CM Pattern recognition and machine learning, Ed. Springer, 2006"},{"key":"319_CR6","volume-title":"Designing social robots","author":"C Breazeal","year":"2001","unstructured":"Breazeal C (2001) Designing social robots. MIT Press, Cambridge, MA"},{"key":"319_CR7","doi-asserted-by":"crossref","unstructured":"Brian CJ Moore (1997) An introduction to the psychology of hearing, Academic Press","DOI":"10.1163\/9789004658820"},{"key":"319_CR8","unstructured":"Burkhardt F, Sendlmeier W (2000) Verification of acoustical correlates of emotional speech using formant-synthesis, Proceedings of the ISCA Workshop on Speech and Emotion"},{"key":"319_CR9","doi-asserted-by":"crossref","unstructured":"Burkhardt F, Paeschke A, Rolfes M, Sendlmeier W, Weiss BA (2005) Database of German Emotional Speech Proceedings Interspeech, Lisbon, Portugal","DOI":"10.21437\/Interspeech.2005-446"},{"issue":"11","key":"319_CR10","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1109\/29.46561","volume":"37","author":"DG Childers","year":"1989","unstructured":"Childers DG, Hand M, Larar JM (1989) Silent and voiced\/unvoied\/ mixed excitation(four-way), classification of speech. IEEE Transaction on ASSP 37(11):1771\u20131774","journal-title":"IEEE Transaction on ASSP"},{"issue":"1","key":"319_CR11","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1142\/S0218348X97000103","volume":"5","author":"A Cohen","year":"1997","unstructured":"Cohen A, Mantegna RN, Havlin S (1997) Numerical analysis of word frequencies in artificial and natural language texts. Fractals 5(1):95\u2013104. doi: 10.1142\/S0218348X97000103","journal-title":"Fractals"},{"issue":"1","key":"319_CR12","first-page":"73","volume":"12","author":"E Dellandrea","year":"2004","unstructured":"Dellandrea E, Makris P, Vincent N (2004) Zipf analysis of audio signals, fractals. World Sci Publishing Co 12(1):73\u201385","journal-title":"World Sci Publishing Co"},{"key":"319_CR13","doi-asserted-by":"crossref","unstructured":"Devillers L, Lamel L (2003) Emotion detection in task-oriented dialogs, proceedings of the ICME 2003, IEEE, Multimedia Human-Machine Interface and Interaction I, Vol.III, pp.549-552, Baltimore, MD, USA","DOI":"10.1109\/ICME.2003.1221370"},{"key":"319_CR14","volume-title":"Robots for fids: exploring new technologies for learning","author":"A Druin","year":"2000","unstructured":"Druin A, Hendler J (2000) Robots for fids: exploring new technologies for learning. Morgan Kauffman, Los Altos, CA"},{"key":"319_CR15","unstructured":"Ekman P Emotions in the human face, Cambridge University Press, 1982"},{"key":"319_CR16","unstructured":"Engberg IS, Hansen AV (1996) Documentation of the Danish Emotional Speech Database DES, Aalborg"},{"issue":"2","key":"319_CR17","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1007\/s10844-005-0322-8","volume":"24","author":"H Harb","year":"2005","unstructured":"Harb H, Chen L (2005) Voice-based gender identification in multimedia applications. J Intell Inf Syst 24(2):179\u2013198","journal-title":"J Intell Inf Syst"},{"key":"319_CR18","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/0378-4371(95)00069-J","volume":"216","author":"S Havlin","year":"1995","unstructured":"Havlin S (1995) The distance between Zipf Plots. Physica A 216:148\u2013150. doi: 10.1016\/0378-4371(95)00069-J","journal-title":"Physica A"},{"key":"319_CR19","unstructured":"http:\/\/emotion-research.net"},{"issue":"6","key":"319_CR20","first-page":"1797","volume":"16","author":"PN Juslin","year":"2000","unstructured":"Juslin PN (2000) Cue utilization in communication of emotion in music performance: relating performance to perception. J Exp Psychol 16(6):1797\u20131813","journal-title":"J Exp Psychol"},{"key":"319_CR21","doi-asserted-by":"crossref","unstructured":"Kusahara M (2001) The art of creating subjective reality: an analysis of Japanese digital pets. In: Boudreau E (ed) in artificial life 7 workshop proceedings, p141\u2013144","DOI":"10.1162\/00240940152549203"},{"key":"319_CR22","unstructured":"McGilloway S, Cowie R, Cowie ED, Gielen S, Westerdijk M, Stroeve S (2000) Approaching automatic recognition of emotion from voice: a rough benchmark, Proceedings of the ISCA workshop on Speech and Emotion, p. 207\u2013212, Newcastle, Northern Ireland"},{"key":"319_CR23","doi-asserted-by":"crossref","first-page":"1356","DOI":"10.1016\/j.jnca.2006.09.005","volume":"30","author":"D Morrison","year":"2007","unstructured":"Morrison D, Silva LCD (2007) Voting ensembles for spoken affect classification. J Netw Comput Appl 30:1356\u20131365. doi: 10.1016\/j.jnca.2006.09.005","journal-title":"J Netw Comput Appl"},{"issue":"1\u20132","key":"319_CR24","first-page":"157","volume":"59","author":"PY Oudeyer","year":"2003","unstructured":"Oudeyer PY (2003) The production and recognition of emotions in speech: features and algorithms. Int J Hum Comput Stud 59(1\u20132):157\u2013183. doi: 10.1016\/S1071-5819(02)00141-6","journal-title":"Int J Hum Comput Stud"},{"key":"319_CR25","unstructured":"Pereira C (2000) Dimensions of emotional meaning in speech, Proceedings of the ISCA workshop on speech and emotion p. 25\u201328, Newcastle, Northern Ireland"},{"key":"319_CR26","doi-asserted-by":"crossref","unstructured":"Picard R (1997) Affective computing. MIT Press","DOI":"10.1037\/e526112012-054"},{"key":"319_CR27","unstructured":"Polzin T, Waibel A (2000) Emotion-sensitive human-computer interfaces, Proceedings of the ISCA workshop on Speech and Emotion, p. 201\u2009~\u2009206, Newcastle, Northern Ireland"},{"issue":"9\/10","key":"319_CR28","first-page":"341","volume":"5","author":"PRAAT","year":"2001","unstructured":"PRAAT (2001) A system for doing phonetics by computer. Glot Int 5(9\/10):341\u2013345","journal-title":"Glot Int"},{"key":"319_CR29","unstructured":"Rakotomalala R (2005) TANAGRA : un logiciel gratuit pour l'enseignement et la recherche, in Actes de EGC'2005, RNTI-E-3, vol. 2, pp. 697-702"},{"key":"319_CR30","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.1037\/h0077714","volume":"39","author":"JA Russel","year":"1980","unstructured":"Russel JA (1980) A circumplex model of affect. J Pers Soc Psychol 39:1161\u20131178. doi: 10.1037\/h0077714","journal-title":"J Pers Soc Psychol"},{"key":"319_CR31","first-page":"165","volume-title":"Handbook of psychophysiology: emotion and social behavior","author":"KR Scherer","year":"1989","unstructured":"Scherer KR (1989) Vocal correlates of emotion. In: Manstead A, Wagner H (eds) Handbook of psychophysiology: emotion and social behavior. Wiley, London, pp 165\u2013197"},{"key":"319_CR32","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/S0167-6393(02)00084-5","volume":"40","author":"KR Scherer","year":"2002","unstructured":"Scherer KR (2002) Vocal communication of emotion: a review of research paradigms. Speech Commun 40:227\u2013256. doi: 10.1016\/S0167-6393(02)00084-5","journal-title":"Speech Commun"},{"key":"319_CR33","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/978-3-642-73769-5_13","volume-title":"Primate vocal communication","author":"KR Scherer","year":"1988","unstructured":"Scherer KR, Kappas A (1988) Primate vocal expression of affective state. In: Todt D, Goedeking P, Symmes D (eds) Primate vocal communication. Springer, Berlin, pp 171\u2013194"},{"key":"319_CR34","doi-asserted-by":"crossref","unstructured":"Scherer KR, Johnstone T, Klasmeyer G, Banziger T (2000) Can automatic speaker verification be improved by training the algorithms on emotional speech? Proc.ICSLP2000, Beijing, China","DOI":"10.21437\/ICSLP.2000-392"},{"key":"319_CR35","doi-asserted-by":"crossref","unstructured":"Scherer KR, Schorr A, Johnstone T (2001) Appraisal processes in emotion: theory, methods, research, Oxford University Press, New York and Oxford","DOI":"10.1093\/oso\/9780195130072.001.0001"},{"key":"319_CR36","doi-asserted-by":"crossref","unstructured":"Schuller B, Rigoll G, Lang M (2003) Hidden markov model-based speech emotion recognition. Proceedings of ICASSP 2003, pp.II-1-II-4","DOI":"10.1109\/ICME.2003.1220939"},{"key":"319_CR37","doi-asserted-by":"crossref","unstructured":"Schuller B, Rigoll G, Lang M (2004) Speech emotion recognition combining acoustic features and linguistic information in hybrid support vector machine \u2212 belief network architecture, proceedings of ICASSP, pp I-577-I-580","DOI":"10.1109\/ICASSP.2004.1326051"},{"key":"319_CR38","doi-asserted-by":"crossref","unstructured":"Schuller B, Reiter S, Muller R, Al-Hames M, Lang M, Rigoll G (2005) Speaker independent speech emotion recognition by ensemble classification, ICME, pp. 864\u2013867","DOI":"10.1109\/ICME.2005.1521560"},{"key":"319_CR39","first-page":"5","volume":"2006","author":"B Schuller","year":"2006","unstructured":"Schuller B, Reiter S, Rigoll G (2006) Evolutionary feature generation in speech emotion recognition. ICME 2006:5\u20138","journal-title":"ICME"},{"key":"319_CR40","doi-asserted-by":"crossref","unstructured":"Schuller B, Wimmer M, M\u00f6senlechner L, Kern C, Arsic D, Rigoll G (2008) Brute-forcing hierarchical functional for paralinguistics : a waste of feature space. Proceedings of Icassp, pp 4501\u20134504","DOI":"10.1109\/ICASSP.2008.4518656"},{"key":"319_CR41","unstructured":"Slaney M, Mcroberts G (1998) Baby Ears: A recognition system for affective vocalizations. Proceedings of the ICASSP 1998, Seattle, WA"},{"key":"319_CR42","unstructured":"Spence C, Sajda P (1998) The role of feature selection in building pattern recognizers for computer-aided diagnosis, Proceedings of SPIE - Volume 3338, Medical Imaging 1998: Image Processing, Kenneth M. Hanson, Editor, p 1434\u20131441"},{"key":"319_CR43","doi-asserted-by":"crossref","unstructured":"Thayer RE (1989) The biopsychology of mood and arousal. Oxford Univ. Press","DOI":"10.1093\/oso\/9780195068276.001.0001"},{"key":"319_CR44","unstructured":"Tickle A (2000) English and Japanese speaker\u2019s emotion vocalizations and recognition: a comparison highlighting vowel quality, ISCA Workshop on Speech and Emotion, Belfast"},{"key":"319_CR45","unstructured":"Ververidis D, Kotropoulos C (2004) Automatic speech classification to five emotional states based on gender information, Proceedings of 12th European Signal Processing Conference, p 341\u2013344, Austria"},{"key":"319_CR46","unstructured":"Ververidis D Kotropoulos C (2005) Emotional speech classification using gaussian mixture models and the sequential floating forward selection algorithm, IEEE International Conference on Multimedia and Expo, ICME, p. 1500\u2013 1503"},{"key":"319_CR47","doi-asserted-by":"crossref","unstructured":"Ververidis D, Kotropoulos C, Pitas I (2004) Automatic emotional speech classification. Proceedings of ICASSP 2004, pp 593\u2013596, Montreal, Canada","DOI":"10.1109\/ICASSP.2004.1326055"},{"key":"319_CR48","doi-asserted-by":"crossref","unstructured":"Voght T, Andr\u00e9 E (2005) Comparing feature sets for acted and spontaneous speech in view of automatic emotion recognition, in Proc. Multimedia and Expo (ICME 2005), Amsterdam, pp.474\u2013477","DOI":"10.1109\/ICME.2005.1521463"},{"key":"319_CR49","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1037\/0033-2909.98.2.219","volume":"98","author":"D Watson","year":"1985","unstructured":"Watson D, Tellegen A (1985) Toward a Consensual Structure of Mood. Psychol Bull 98:219\u2013235. doi: 10.1037\/0033-2909.98.2.219","journal-title":"Psychol Bull"},{"key":"319_CR50","doi-asserted-by":"crossref","unstructured":"Wieczorkowska A, Synak P, Lewis R, Ras ZW (2005) Extracting emotions from music data. Proceedings of 15th International Symposium, ISMIS 2005, p. 456\u2013465, Saratoga Springs, NY, USA","DOI":"10.1007\/11425274_47"},{"key":"319_CR51","volume-title":"Data mining: practical machine learning tools and techniques with Java implementations","author":"IH Witten","year":"2000","unstructured":"Witten IH, Frank E (2000) Data mining: practical machine learning tools and techniques with Java implementations. Morgan Kaufmann, San Francisco, CA, USA"},{"key":"319_CR52","unstructured":"Xiao Z, Dellandrea E, Dou W, Chen L (2005) Features extraction and selection in emotional speech, International Conference on Advanced Video and Signal based Surveillance (AVSS 2005). p. 411\u2013416., Como, Italy"},{"key":"319_CR53","doi-asserted-by":"crossref","unstructured":"Xiao Z, Dellandrea E, Dou W, Chen L (2006) Two-stage classification of emotional speech, International Conference on Digital Telecommunications (ICDT'06), p. 32\u201337, Cap Esterel, C\u00f4te d\u2019Azur, France","DOI":"10.1109\/ICDT.2006.76"},{"key":"319_CR54","doi-asserted-by":"crossref","unstructured":"Xiao Z, Dellandrea E, Dou W, Chen L (2007) Automatic hierarchical classification of emotional speech, Ninth IEEE International Symposium on Multimedia Workshops (ISMW 2007), p. 291\u2013296, Taiwan","DOI":"10.1109\/ISM.Workshops.2007.56"},{"key":"319_CR55","doi-asserted-by":"crossref","unstructured":"Xiao Z, Dellandrea E, Dou W, Chen L (2007) Hierarchical classification of emotional speech, research report RR-LIRIS-2007-006, LIRIS UMR 5205 CNRS","DOI":"10.1109\/ISM.Workshops.2007.56"},{"key":"319_CR56","unstructured":"Zipf GK (1949) Human behavior and the principle of least effort. Addison-Wesley Press, 1949"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-009-0319-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-009-0319-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-009-0319-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,10]],"date-time":"2025-02-10T19:57:20Z","timestamp":1739217440000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-009-0319-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,7,9]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2010,1]]}},"alternative-id":["319"],"URL":"https:\/\/doi.org\/10.1007\/s11042-009-0319-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2009,7,9]]}}}