{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T15:27:42Z","timestamp":1767626862828},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2012,5,17]],"date-time":"2012-05-17T00:00:00Z","timestamp":1337212800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2012,12]]},"DOI":"10.1007\/s10489-012-0352-1","type":"journal-article","created":{"date-parts":[[2012,5,16]],"date-time":"2012-05-16T01:52:07Z","timestamp":1337133127000},"page":"602-612","source":"Crossref","is-referenced-by-count":18,"title":["Mandarin emotion recognition combining acoustic and emotional point information"],"prefix":"10.1007","volume":"37","author":[{"given":"Lijiang","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xia","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuli","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mitsuru","family":"Ishizuka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,5,17]]},"reference":[{"key":"352_CR1","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1140.001.0001","volume-title":"Affective computing","author":"R Picard","year":"2000","unstructured":"Picard R (2000) Affective computing. MIT Press, Cambridge"},{"issue":"1","key":"352_CR2","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1007\/s10489-007-0076-9","volume":"30","author":"L Malatesta","year":"2009","unstructured":"Malatesta L, Raouzaiou A, Karpouzis K, Kollias S (2009) Towards modeling embodied conversational agent character profiles using appraisal theory predictions in expression synthesis. Appl Intell 30(1):58\u201364","journal-title":"Appl Intell"},{"issue":"2","key":"352_CR3","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1023\/A:1013614519179","volume":"16","author":"S Cho","year":"2002","unstructured":"Cho S (2002) Towards creative evolutionary systems with interactive genetic algorithm. Appl Intell 16(2):129\u2013138","journal-title":"Appl Intell"},{"key":"352_CR4","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1007\/11573548_125","volume-title":"Proc of affective computing and intelligent interaction","author":"J Tao","year":"2005","unstructured":"Tao J, Tan T (2005) Affective computing: a review. In: Proc of affective computing and intelligent interaction, pp 981\u2013995"},{"issue":"3","key":"352_CR5","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1007\/s10489-009-0169-8","volume":"33","author":"K Assaleh","year":"2010","unstructured":"Assaleh K, Shanableh T (2010) Robust polynomial classifier using L 1-norm minimization. Appl Intell 33(3):330\u2013339","journal-title":"Appl Intell"},{"issue":"3","key":"352_CR6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10489-011-0285-0","volume":"34","author":"G Ince","year":"2011","unstructured":"Ince G, Nakadai K, Rodemann T, Tsujino H, Imura J (2011) Ego noise cancellation of a robot using missing feature masks. Appl Intell 34(3):1\u201312","journal-title":"Appl Intell"},{"issue":"9","key":"352_CR7","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(9):1162\u20131181","journal-title":"Speech Commun"},{"issue":"1\u20132","key":"352_CR8","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/S0167-6393(02)00084-5","volume":"40","author":"K Scherer","year":"2003","unstructured":"Scherer K (2003) Vocal communication of emotion: a review of research paradigms. Speech Commun 40(1\u20132):227\u2013256","journal-title":"Speech Commun"},{"key":"352_CR9","first-page":"222","volume-title":"Sixth international conference on spoken language processing","author":"VA Petrushin","year":"2000","unstructured":"Petrushin VA (2000) Emotion recognition in speech signal: experimental study, development, and application. In: Sixth international conference on spoken language processing, Beijing, China, vol\u00a02, pp\u00a0222\u2013225"},{"key":"352_CR10","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1007\/978-3-540-73729-2_43","volume-title":"Proc of modeling decisions for artificial intelligence","author":"W Yoon","year":"2007","unstructured":"Yoon W, Park K (2007) A study of emotion recognition and its applications. In: Proc of modeling decisions for artificial intelligence, pp 455\u2013462"},{"issue":"12","key":"352_CR11","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(12):1760\u20131774","journal-title":"Image Vis Comput"},{"issue":"3\u20134","key":"352_CR12","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1080\/02699939208411068","volume":"6","author":"P Ekman","year":"1992","unstructured":"Ekman P (1992) An argument for basic emotions. Cogn Emot 6(3\u20134):169\u2013200","journal-title":"Cogn Emot"},{"key":"352_CR13","volume-title":"Emotion: a psychoevolutionary synthesis","author":"R Plutchik","year":"1980","unstructured":"Plutchik R (1980) Emotion: a psychoevolutionary synthesis. Harper Collins, New York"},{"key":"352_CR14","volume-title":"An approach to environmental psychology","author":"A Mehrabian","year":"1974","unstructured":"Mehrabian A, Russell J (1974) An approach to environmental psychology. MIT Press, Cambridge"},{"issue":"1","key":"352_CR15","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1057\/thr.2009.18","volume":"10","author":"A Coghlan","year":"2010","unstructured":"Coghlan A, Pearce P (2010) Tracking affective components of satisfaction. Tour Hosp Res 10(1):42","journal-title":"Tour Hosp Res"},{"issue":"3","key":"352_CR16","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, Scherer K (1996) Acoustic profiles in vocal emotion expression. J Pers Soc Psychol 70(3):614","journal-title":"J Pers Soc Psychol"},{"issue":"5","key":"352_CR17","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(5):1415\u20131423","journal-title":"Signal Process"},{"key":"352_CR18","first-page":"1","volume-title":"Proceedings of speech prosody 2004","author":"H Fujisaki","year":"2004","unstructured":"Fujisaki H (2004) Information, prosody, and modeling-with emphasis on tonal features of speech. In: Proceedings of speech prosody 2004, Nara, Japan, pp 1\u201310"},{"key":"352_CR19","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1007\/11573548_40","volume-title":"Proc of affective computing and intelligent interaction","author":"L Zhao","year":"2005","unstructured":"Zhao L, Cao Y, Wang Z, Zou C (2005) Speech emotional recognition using global and time sequence structure features with MMD. In: Proc of affective computing and intelligent interaction, pp 311\u2013318"},{"key":"352_CR20","first-page":"1","volume-title":"2005 IEEE international conference on multimedia and expo","author":"M Shami","year":"2005","unstructured":"Shami M, Kamel M (2005) Segment-based approach to the recognition of emotions in speech. In: 2005 IEEE international conference on multimedia and expo. IEEE Press, New York, pp 1\u20134"},{"key":"352_CR21","first-page":"I577","volume-title":"IEEE international conference on acoustics, speech, and signal processing. Proceedings ICASSP\u201904","author":"B Schuller","year":"2004","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: IEEE international conference on acoustics, speech, and signal processing. Proceedings ICASSP\u201904, vol 1. IEEE Press, New York, pp\u00a0I577\u2013I580"},{"issue":"3","key":"352_CR22","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1016\/j.specom.2004.01.001","volume":"42","author":"J Zhang","year":"2004","unstructured":"Zhang J, Hirose K (2004) Tone nucleus modeling for Chinese lexical tone recognition. Speech Commun 42(3):447\u2013466","journal-title":"Speech Commun"},{"key":"352_CR23","volume-title":"A grammar of spoken Chinese","author":"Y Chao","year":"1965","unstructured":"Chao Y (1965) A grammar of spoken Chinese. University of California Press, Berkeley"},{"key":"352_CR24","volume-title":"Speech signal processing","author":"Y Chen","year":"1990","unstructured":"Chen Y, Wang R (1990) Speech signal processing. University of Science and Technology of China Press, Hefei (in Chinese)"},{"issue":"8","key":"352_CR25","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.1016\/0167-8191(95)00017-I","volume":"21","author":"C Olson","year":"1995","unstructured":"Olson C (1995) Parallel algorithms for hierarchical clustering. Parallel Comput 21(8):1313\u20131325","journal-title":"Parallel Comput"},{"issue":"8","key":"352_CR26","doi-asserted-by":"crossref","first-page":"2324","DOI":"10.1587\/transinf.E93.D.2324","volume":"93","author":"X Mao","year":"2010","unstructured":"Mao X, Chen L (2010) Speech emotion recognition based on parametric filter and fractal dimension. IEICE Trans Inf Syst 93(8):2324\u20132326","journal-title":"IEICE Trans Inf Syst"},{"issue":"1","key":"352_CR27","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/s11042-009-0319-3","volume":"46","author":"Z Xiao","year":"2010","unstructured":"Xiao Z, Dellandrea E, Dou W, Chen L (2010) Multi-stage classification of emotional speech motivated by a dimensional emotion model. Multimed Tools Appl 46(1):119\u2013145","journal-title":"Multimed Tools Appl"},{"issue":"4","key":"352_CR28","first-page":"376","volume":"8","author":"R Fisher","year":"1938","unstructured":"Fisher R (1938) The statistical utilization of multiple measurements. Ann Hum Genet 8(4):376\u2013386","journal-title":"Ann Hum Genet"},{"issue":"7","key":"352_CR29","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1109\/34.598228","volume":"19","author":"P Belhumeur","year":"1997","unstructured":"Belhumeur P, Hespanha J, Kriegman D (1997) Eigenfaces vs. fisherfaces: recognition using class specific linear projection. IEEE Trans Pattern Anal Mach Intell 19(7):711\u2013720","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"352_CR30","doi-asserted-by":"crossref","first-page":"2417","DOI":"10.1587\/transinf.E93.D.2417","volume":"93","author":"Y Sun","year":"2010","unstructured":"Sun Y, Zhou Y, Zhao Q, Yan Y (2010) Acoustic feature optimization based on f-ratio for robust speech recognition. IEICE Trans Inf Syst 93(9):2417\u20132430","journal-title":"IEICE Trans Inf Syst"},{"issue":"11","key":"352_CR31","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.1016\/0167-8655(94)90127-9","volume":"15","author":"P Pudil","year":"1994","unstructured":"Pudil P, Novovicov\u00e1 J, Kittler J (1994) Floating search methods in feature selection. Pattern Recognit Lett 15(11):1119\u20131125","journal-title":"Pattern Recognit Lett"},{"issue":"3","key":"352_CR32","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273\u2013297","journal-title":"Mach Learn"},{"key":"352_CR33","doi-asserted-by":"crossref","first-page":"4898","DOI":"10.1109\/ICMLC.2005.1527805","volume-title":"Proceedings of 2005 international conference on machine learning and cybernetics","author":"Y Lin","year":"2005","unstructured":"Lin Y, Wei G (2005) Speech emotion recognition based on HMM and SVM. In: Proceedings of 2005 international conference on machine learning and cybernetics, vol 8. IEEE Press, New York, pp 4898\u20134901"},{"key":"352_CR34","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1109\/ICME.2005.1521560","volume-title":"IEEE international conference on multimedia and expo, 2005. ICME 2005","author":"B Schuller","year":"2005","unstructured":"Schuller B, Reiter S, Muller R, Al-Hames M, Lang M, Rigoll G (2005) Speaker independent speech emotion recognition by ensemble classification. In: IEEE international conference on multimedia and expo, 2005. ICME 2005. IEEE Press, New York, pp\u00a0864\u2013867"},{"issue":"1","key":"352_CR35","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1023\/A:1008359903796","volume":"12","author":"R Damper","year":"2000","unstructured":"Damper R, Gunn S, Gore M (2000) Extracting phonetic knowledge from learning systems: perceptrons, support vector machines and linear discriminants. Appl Intell 12(1):43\u201362","journal-title":"Appl Intell"},{"key":"352_CR36","doi-asserted-by":"crossref","first-page":"525","DOI":"10.2307\/412031","volume":"48","author":"J Hooper","year":"1972","unstructured":"Hooper J (1972) The syllable in phonological theory. Language 48:525\u2013540","journal-title":"Language"},{"issue":"4","key":"352_CR37","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1177\/00238309010440040101","volume":"44","author":"J Goslin","year":"2001","unstructured":"Goslin J, Frauenfelder U (2001) A comparison of theoretical and human syllabification. Lang Speech 44(4):409\u2013436","journal-title":"Lang Speech"},{"issue":"1\u20133","key":"352_CR38","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/S0167-6393(98)00033-8","volume":"25","author":"O Viikki","year":"1998","unstructured":"Viikki O, Laurila K (1998) Cepstral domain segmental feature vector normalization for noise robust speech recognition. Speech Commun 25(1\u20133):133\u2013147","journal-title":"Speech Commun"},{"key":"352_CR39","first-page":"733","volume-title":"Proceedings of the 1998 IEEE international conference on acoustics, speech and signal processing, 1998","author":"O Viikki","year":"1998","unstructured":"Viikki O, Bye D, Laurila K (1998) A recursive feature vector normalization approach for robust speech recognition in noise. In: Proceedings of the 1998 IEEE international conference on acoustics, speech and signal processing, 1998, vol 2. IEEE Press, New York, pp 733\u2013736"},{"key":"352_CR40","doi-asserted-by":"crossref","first-page":"2277","DOI":"10.1109\/ICSLP.1996.607261","volume-title":"Proceedings of fourth international conference on spoken language, ICSLP 96","author":"J Glass","year":"1996","unstructured":"Glass J, Chang J, McCandless M (1996) A probabilistic framework for feature-based speech recognition. In: Proceedings of fourth international conference on spoken language, ICSLP 96, vol 4. IEEE Press, New York, pp 2277\u20132280"},{"key":"352_CR41","first-page":"2679","volume-title":"Proceedings of eurospeech, 2001","author":"A Nogueiras","year":"2001","unstructured":"Nogueiras A, Moreno A, Bonafonte A, Mari\u00f1o J (2001) Speech emotion recognition using hidden Markov models. In: Proceedings of eurospeech, 2001, pp 2679\u20132682"},{"issue":"1\u20132","key":"352_CR42","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/S0167-6393(02)00080-8","volume":"40","author":"R Fernandez","year":"2003","unstructured":"Fernandez R, Picard R (2003) Modeling drivers\u2019 speech under stress. Speech Commun 40(1\u20132):145\u2013159","journal-title":"Speech Commun"},{"issue":"2","key":"352_CR43","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s10489-008-0152-9","volume":"33","author":"M Janev","year":"2010","unstructured":"Janev M, Pekar D, Jakovljevic N, Delic V (2010) Eigenvalues driven Gaussian selection in continuous speech recognition using HMMS with full covariance matrices. Appl Intell 33(2):107\u2013116","journal-title":"Appl Intell"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-012-0352-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10489-012-0352-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-012-0352-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,7]],"date-time":"2020-07-07T18:50:42Z","timestamp":1594147842000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10489-012-0352-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,5,17]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2012,12]]}},"alternative-id":["352"],"URL":"https:\/\/doi.org\/10.1007\/s10489-012-0352-1","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,5,17]]}}}