{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T06:29:56Z","timestamp":1764224996468},"publisher-location":"Berlin, Heidelberg","reference-count":38,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642123962"},{"type":"electronic","value":"9783642123979"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-12397-9_21","type":"book-chapter","created":{"date-parts":[[2010,3,26]],"date-time":"2010-03-26T16:06:10Z","timestamp":1269619570000},"page":"255-267","source":"Crossref","is-referenced-by-count":13,"title":["Emotional Vocal Expressions Recognition Using the COST 2102 Italian Database of Emotional Speech"],"prefix":"10.1007","author":[{"given":"Hicham","family":"Atassi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria Teresa","family":"Riviello","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zden\u011bk","family":"Sm\u00e9kal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir","family":"Hussain","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Esposito","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"21_CR1","unstructured":"Christian, J., Deeming, A.: Affective Human-Robotic Interaction. Affect and Emotion in Human-Computer Interaction: From Theory to Applications, Christian Peter, Russell Beale (2008)"},{"key":"21_CR2","unstructured":"Sony AIBO Europe, Sony Entertainment, http:\/\/www.sonydigital-link.com\/AIBO\/"},{"key":"21_CR3","unstructured":"Petrushin, V.: Emotion in Speech: Recognition and Application to Call Centers. In: Proceedings of the Conference on Artificial Neural Networks in Engineering, pp. 7\u201310 (1999)"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Van Bezooijen, R.: The Characteristics and Recognisability of Vocal Expression of Emotions. Drodrecht, The Netherlands, Foris (1984)","DOI":"10.1515\/9783110850390"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Rahurkar, M., Hansen, J.H.L.: Frequency Band Analysis for Stress Detection Using Teager energy Operator Based Feature. In: Proc. Int. Conf. Spoken Language Processing (ICSLP 2002), vol.\u00a03, pp. 2021\u20132024 (2002)","DOI":"10.21437\/ICSLP.2002-555"},{"key":"21_CR6","doi-asserted-by":"publisher","first-page":"1117","DOI":"10.1109\/TASL.2006.876121","volume":"14","author":"E. Navas","year":"2006","unstructured":"Navas, E., Hern\u00e1ez, L.I.: An Objective and Subjective Study of the Role of Semantics and Prosodic Features in Building Corpora for Emotional TTS. IEEE Transactions on Audio, Speech, and Language Processing\u00a014, 1117\u20131127 (2006)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"21_CR7","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1109\/ICTAI.2008.158","volume-title":"Proc. of 20th Int. Conf. Tools with Artificial Intelligence, ICTAI 2008","author":"H. Atassi","year":"2008","unstructured":"Atassi, H., Esposito, A.: A Speaker Independent Approach to the Classification of Emotional Vocal Expressions. In: Proc. of 20th Int. Conf. Tools with Artificial Intelligence, ICTAI 2008, pp. 147\u2013151. IEEE Computer Society, Dayton (2008)"},{"key":"21_CR8","first-page":"279","volume":"2","author":"P. Pudil","year":"1994","unstructured":"Pudil, P., Ferri, F., Novovicova, J., Kittler, J.: Floating search method for feature selection with non monotonic criterion functions. Pattern Recognition\u00a02, 279\u2013283 (1994)","journal-title":"Pattern Recognition"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W., Weiss, B.: A Database of German Emotional Speech. In: Proceedings of Interspeech, pp. 1517\u20131520 (2005)","DOI":"10.21437\/Interspeech.2005-446"},{"key":"21_CR10","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1111\/j.1467-9280.1992.tb00253.x","volume":"3","author":"P. Ekman","year":"1992","unstructured":"Ekman, P.: Facial expression of emotion: New findings, new questions. Psychological Science\u00a03, 34\u201338 (1992)","journal-title":"Psychological Science"},{"key":"21_CR11","volume-title":"Understanding emotions","author":"K. Oatley","year":"1996","unstructured":"Oatley, K., Jenkins, J.M.: Understanding emotions. Blackwell, Oxford (1996)"},{"issue":"3","key":"21_CR12","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1037\/0022-3514.70.3.614","volume":"70","author":"R. Banse","year":"1996","unstructured":"Banse, R., Scherer, K.: Acoustic profiles in vocal emotion expression. Journal of Personality & Social Psychology\u00a070(3), 614\u2013636 (1996)","journal-title":"Journal of Personality & Social Psychology"},{"key":"21_CR13","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/S0167-6393(02)00084-5","volume":"40","author":"K.R. Scherer","year":"2003","unstructured":"Scherer, K.R.: Vocal communication of emotion: A review of research paradigms. Speech Communication\u00a040, 227\u2013256 (2003)","journal-title":"Speech Communication"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Scherer, K.R., Banse, R., Wallbott, H.G.: Emotion inferences from vocal expression correlate across languages and cultures. Journal of Cross-Cultural Psychology, 76\u201392 (2001)","DOI":"10.1177\/0022022101032001009"},{"key":"21_CR15","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00995674","volume":"15","author":"K.R. Scherer","year":"1991","unstructured":"Scherer, K.R., Banse, R., Wallbott, H.G., Goldbeck, T.: Vocal cues in emotion encoding and decoding. Motivation and Emotion\u00a015, 123\u2013148 (1991)","journal-title":"Motivation and Emotion"},{"key":"21_CR16","first-page":"165","volume-title":"Handbook of social Psychophysiology","author":"K.R. Scherer","year":"1989","unstructured":"Scherer, K.R.: Vocal correlates of emotional arousal and affective disturbance. In: Wagner, H., Manstead, A. (eds.) Handbook of social Psychophysiology, pp. 165\u2013197. Wiley, New York (1989)"},{"key":"21_CR17","volume-title":"To be published in Proceedings of WIRN 2009","author":"A. Esposito","year":"2009","unstructured":"Esposito, A., Riviello, M.T., Di Maio, G.: The COST 2102 Italian Audio and Video Emotional Database. In: To be published in Proceedings of WIRN 2009, Vietri sul Mare, May 28-30, IOS press, Amsterdam (2009)"},{"key":"21_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/978-3-642-10308-7_9","volume-title":"USAB 2009,","author":"A. Esposito","year":"2009","unstructured":"Esposito, A., Riviello, M.T., Bourbakis, N.: Cultural Specific Effects on the Recognition of Basic Emotions: A Study on Italian Subjects. In: Holzinger, A. (ed.) USAB 2009. LNCS, vol.\u00a05889, pp. 135\u2013148. Springer, Heidelberg (2009)"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Schuller, B., Rigoll, G., Lang, M.: Hidden Markov Model-Based Speech Emotion Recognition. In: Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2003, Hong Kong, China, vol.\u00a02 (2003)","DOI":"10.1109\/ICME.2003.1220939"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Nogueiras, A., Marino, J.B., Moreno, A., Bonafonte, A.: Speech emotion recognition using hidden Markov models. In: Proc. European Conf. Speech Communication and Technology (Eurospeech 2001), Denmark (2001)","DOI":"10.21437\/Eurospeech.2001-627"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Ververidis, D., Kotropoulos, C.: Emotional speech classification using Gaussian mixture models and the sequential floating forward selection algorithm. In: Proc. Int. Conf. Multimedia and Expo, ICME 2005 (2005)","DOI":"10.1109\/ICME.2005.1521717"},{"key":"21_CR22","unstructured":"Ververidis, D., Kotropoulos, C.: Automatic Speech Classification to five emotional states based on gender information. In: Proc. 12th European Signal Processing Conf., Vienna, pp. 341\u2013344 (2004)"},{"key":"21_CR23","unstructured":"Pao, T., Chen, Y., Yeh, J.: Emotion Recognition from Mandarin Speech Signals. In: International Symposium on Spoken Language Processing, Chinese (2004)"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Lugger, M., Yang, B.: The Relevance of Voice Quality Features in Speaker Independent Emotion Recognition. In: Proceedings of ICASSP, Honolulu, Hawaii (2007)","DOI":"10.1109\/ICASSP.2007.367152"},{"key":"21_CR25","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1016\/S0167-6393(03)00099-2","volume":"41","author":"T.L. Nwe","year":"2003","unstructured":"Nwe, T.L., Foo, S.W., De Silva, L.C.: Speech emotion recognition using hidden Markov models. Speech Communication\u00a041, 603\u2013623 (2003)","journal-title":"Speech Communication"},{"key":"21_CR26","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1121\/1.399423","volume":"4","author":"H. Hermansky","year":"1990","unstructured":"Hermansky, H.: Perceptual Linear Predictive (PLP) Analysis of Speech. Journal of Acoustic Socienty\u00a0(4), 1738\u20131753 (1990)","journal-title":"Journal of Acoustic Socienty"},{"key":"21_CR27","unstructured":"Apolloni, B., Aversano, G., Esposito, A.: Preprocessing and Classification of Emotional Features in Speech Sentences. In: Kosarev, Y. (ed.) Proc. of International Workshop on Speech and Computer, SPIIRAS, pp. 49\u201352 (2000)"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Busso, C., Lee, S., Narayanan, S.S.: Using Neutral Speech Models for Emotional Speech Analysis. In: Interspeech- Eurospeech, Antwerp, Belgium, pp. 2225\u20132228 (2007)","DOI":"10.21437\/Interspeech.2007-605"},{"key":"21_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-540-75555-5_1","volume-title":"Advances in Brain, Vision, and Artificial Intelligence","author":"V. Stejskal","year":"2007","unstructured":"Stejskal, V., Smekal, Z., Esposito, A., Bourbakis, N.: The Significance of Empty Speech Pauses: Cognitive and Algorithmic Issues. In: Mele, F., Ramella, G., Santillo, S., Ventriglia, F. (eds.) BVAI 2007. LNCS, vol.\u00a04729, pp. 1\u201313. Springer, Heidelberg (2007)"},{"key":"21_CR30","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/11520153_12","volume-title":"Nonlinear Speech Modeling and Applications","author":"A. Esposito","year":"2005","unstructured":"Esposito, A., Aversano, G.: Text Independent Methods for Speech Segmentation. In: Chollet, G., Esposito, A., Fa\u00fandez-Zanuy, M., Marinaro, M. (eds.) Nonlinear Speech Modeling and Applications. LNCS (LNAI), vol.\u00a03445, pp. 261\u2013290. Springer, Heidelberg (2005)"},{"key":"21_CR31","volume-title":"Pattern Classification","author":"R. Duda","year":"2003","unstructured":"Duda, R., Hart, P., Stork, D.: Pattern Classification, 2nd edn. Wiley, Chichester (2003)","edition":"2"},{"key":"21_CR32","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1007\/978-3-540-69369-7_22","volume-title":"Perception in Multimodal Dialogue Systems","author":"S. Scherer","year":"2008","unstructured":"Scherer, S., Oubbati, M., Schwenker, F., Palm, G.: Real-time emotion recognition using echo state model. In: Andr\u00e9, E., Dybkj\u00e6r, L., Minker, W., Neumann, H., Pieraccini, R., Weber, M. (eds.) PIT 2008. LNCS (LNAI), vol.\u00a05078, pp. 200\u2013204. Springer, Heidelberg (2008)"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Lee, C., Narayanan, S.: Emotion recognition using a data-driven fuzzy inference system. In: Proceedings of Eurospeech, pp. 157\u2013160 (2003)","DOI":"10.21437\/Eurospeech.2003-88"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Schuller, B., Rigoll, G., Lang, M.: Speech emotion recognition combining acoustic features and linguistic information in a hybrid support vector machine-belief network architecture. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP 2004), vol.\u00a01, pp. 557\u2013560 (2004)","DOI":"10.1109\/ICASSP.2004.1326051"},{"key":"21_CR35","doi-asserted-by":"publisher","DOI":"10.1002\/0471660264","volume-title":"Combining Pattern Classifiers: Methods and Algorithms","author":"L.I. Kuncheva","year":"2004","unstructured":"Kuncheva, L.I.: Combining Pattern Classifiers: Methods and Algorithms. Wiley, Hoboken (2004)"},{"key":"21_CR36","unstructured":"Faundez-Zanuy, M.: Data Fusion at Different Levels. In: Multimodal Signals: Cognitive and Algorithmic Issues: COST Action 2102 and euCognition International School Vietri sul Mare, Italy, pp. 21\u201326 (2008)"},{"issue":"10","key":"21_CR37","first-page":"755","volume":"50","author":"J.G. Beerends","year":"2002","unstructured":"Beerends, J.G., Rix, A.W., Hollier, M.P., Hekstra, A.P.: Perceptual evaluation of speech quality (PESQ) The new ITU standard for end-to-end speech quality assessment, Part I \u2013 Time-Delay Compensation. J. Audio Eng. Soc.\u00a050(10), 755\u2013764 (2002)","journal-title":"J. Audio Eng. Soc."},{"key":"21_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1007\/978-3-642-12397-9","volume-title":"Development of Multimodal Interfaces: Active Listening and Synchrony","author":"A. Esposito","year":"2010","unstructured":"Esposito, A., Riviello, T.: The New Italian Audio and Video Emotional Database. In: Esposito, A., et al. (eds.) Development of Multimodal Interfaces: Active Listening and Synchrony. LNCS, vol.\u00a05967, pp. 255\u2013267. Springer, Heidelberg (2010)"}],"container-title":["Lecture Notes in Computer Science","Development of Multimodal Interfaces: Active Listening and Synchrony"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-12397-9_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T08:02:07Z","timestamp":1685520127000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-12397-9_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642123962","9783642123979"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-12397-9_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}