{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T11:49:01Z","timestamp":1751629741168,"version":"3.40.4"},"publisher-location":"Berlin, Heidelberg","reference-count":103,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642345838"},{"type":"electronic","value":"9783642345845"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-34584-5_3","type":"book-chapter","created":{"date-parts":[[2012,11,16]],"date-time":"2012-11-16T07:03:10Z","timestamp":1353049390000},"page":"35-49","source":"Crossref","is-referenced-by-count":11,"title":["Ten Recent Trends in Computational Paralinguistics"],"prefix":"10.1007","author":[{"given":"Bj\u00f6rn","family":"Schuller","sequence":"first","affiliation":[]},{"given":"Felix","family":"Weninger","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Abelin, A.: Cross-Cultural Multimodal Interpretation of Emotional Expressions - An Experimental Study of Spanish and Swedish. In: Proc. of Speech Prosody, ISCA (2004); no pagination","DOI":"10.21437\/SpeechProsody.2004-149"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Ang, J., Dhillon, R., Shriberg, E., Stolcke, A.: Prosody-based automatic detection of annoyance and frustration in human-computer dialog. In: Proc. Interspeech, pp. 2037\u20132040. Denver (2002)","DOI":"10.21437\/ICSLP.2002-559"},{"key":"3_CR3","unstructured":"Baggia, P., Burnett, D.C., Carter, J., Dahl, D.A., McCobb, G., Raggett, D.: EMMA: Extensible MultiModal Annotation markup language (2007), http:\/\/www.w3.org\/TR\/emma\/"},{"key":"3_CR4","doi-asserted-by":"publisher","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., Amir, N.: Whodunnit \u2013 Searching for the Most Important Feature Types Signalling Emotional User States in Speech. Computer Speech and Language\u00a025, 4\u201328 (2011)","journal-title":"Computer Speech and Language"},{"issue":"2","key":"3_CR5","doi-asserted-by":"publisher","first-page":"531","DOI":"10.3758\/BRM.40.2.531","volume":"40","author":"P. Belin","year":"2008","unstructured":"Belin, P., Fillion-Bilodeau, S., Gosselin, F.: The montreal affective voices: A validated set of nonverbal affect bursts for research on auditory affective processing. Behavior Research Methods\u00a040(2), 531\u2013539 (2008)","journal-title":"Behavior Research Methods"},{"key":"3_CR6","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-540-74122-0_10","volume-title":"Speaker Classification II: Selected Projects","author":"J.R. Bellegarda","year":"2007","unstructured":"Bellegarda, J.R.: Language-independent speaker classification over a far-field microphone. In: Mueller, C. (ed.) Speaker Classification II: Selected Projects, pp. 104\u2013115. Springer, Berlin (2007)"},{"issue":"7-8","key":"3_CR7","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1016\/j.specom.2010.02.010","volume":"52","author":"D. Bitouk","year":"2011","unstructured":"Bitouk, D., Verma, R., Nenkova, A.: Class-level spectral features for emotion recognition. Speech Communication\u00a052(7-8), 613\u2013625 (2011)","journal-title":"Speech Communication"},{"key":"3_CR8","volume-title":"Mind as Machine: A History of Cognitive Science, chap","author":"M. Boden","year":"2008","unstructured":"Boden, M.: Mind as Machine: A History of Cognitive Science, ch. 9. Oxford Univ. Press, New York (2008)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Bone, D., Black, M.P., Li, M., Metallinou, A., Lee, S., Narayanan, S.: Intoxicated Speech Detection by Fusion of Speaker Normalized Hierarchical Features and GMM Supervectors. In: Proc. of Interspeech, Florence, Italy, pp. 3217\u20133220 (2011)","DOI":"10.21437\/Interspeech.2011-805"},{"issue":"1-2","key":"3_CR10","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/0167-6393(94)90039-6","volume":"15","author":"D. Byrd","year":"1994","unstructured":"Byrd, D.: Relations of sex and dialect to reduction. Speech Communication\u00a015(1-2), 39\u201354 (1994)","journal-title":"Speech Communication"},{"issue":"9","key":"3_CR11","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.1109\/5.628714","volume":"85","author":"J. Campbell","year":"1997","unstructured":"Campbell, J.: Speaker recognition: a tutorial. Proceedings of the IEEE\u00a085(9), 1437\u20131462 (1997)","journal-title":"Proceedings of the IEEE"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Campbell, N.: On the use of nonverbal speech sounds in human communication. In: Proc. of COST 2102 Workshop, Vietri sul Mare, Italy, pp. 117\u2013128 (2007)","DOI":"10.1007\/978-3-540-76442-7_11"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Campbell, N., Kane, J., Moniz, H.: Processing \u2018yup!\u2019 and other short utterances in interactive speech. In: Proc. of ICASSP, Prague, Czech Republic, pp. 5832\u20135835 (2011)","DOI":"10.1109\/ICASSP.2011.5947687"},{"issue":"4","key":"3_CR14","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1023\/B:JOPR.0000035102.30000.a7","volume":"33","author":"M. Cannizzaro","year":"2004","unstructured":"Cannizzaro, M., Reilly, N., Snyder, P.J.: Speech content analysis in feigned depression. Journal of Psycholinguistic Research\u00a033(4), 289\u2013301 (2004)","journal-title":"Journal of Psycholinguistic Research"},{"key":"3_CR15","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R. Caruana","year":"1997","unstructured":"Caruana, R.: Multitask learning: A knowledge-based source of inductive bias. Machine Learning\u00a028, 41\u201375 (1997)","journal-title":"Machine Learning"},{"key":"3_CR16","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"N.V. Chawla","year":"2002","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research\u00a016, 321\u2013357 (2002)","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"2","key":"3_CR17","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1111\/j.1467-9922.2009.00510.x","volume":"59","author":"A. Chen","year":"2009","unstructured":"Chen, A.: Perception of paralinguistic intonational meaning in a second language. Language Learning\u00a059(2), 367\u2013409 (2009)","journal-title":"Language Learning"},{"issue":"11","key":"3_CR18","doi-asserted-by":"publisher","first-page":"1514","DOI":"10.1177\/0146167210385360","volume":"36","author":"S.X. Chen","year":"2010","unstructured":"Chen, S.X., Bond, M.H.: Two languages, two personalities? examining language effects on the expression of personality in a bilingual context. Personality and Social Psychology Bulletin\u00a036(11), 1514\u20131528 (2010)","journal-title":"Personality and Social Psychology Bulletin"},{"key":"3_CR19","unstructured":"Cowie, R., Douglas-Cowie, E., Savvidou, S., McMahon, E., Sawey, M., Schr\u00f6der, M.: Feeltrace: An instrument for recording perceived emotion in real time. In: Proceedings of the ISCA Workshop on Speech and Emotion, Newcastle, Northern Ireland, pp. 19\u201324 (2000)"},{"key":"3_CR20","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1146\/annurev.ps.41.020190.002221","volume":"41","author":"J.M. Digman","year":"1990","unstructured":"Digman, J.M.: Personality Structure: emergence of the Five-Factor Model. Ann. Rev. Psychol.\u00a041, 417\u2013440 (1990)","journal-title":"Ann. Rev. Psychol."},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Doddington, G., Liggett, W., Martin, A., Przybocki, M., Reynolds, D.: Sheep, Goats, Lambs and Wolves: A Statistical Analysis of Speaker Performance in the NIST 1998 Speaker Recognition Evaluation. In: Proc. of ICSLP (1998); no pagination","DOI":"10.21437\/ICSLP.1998-244"},{"issue":"3","key":"3_CR22","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1177\/002383099503800304","volume":"38","author":"W.A. Dommelen van","year":"1995","unstructured":"van Dommelen, W.A., Moxness, B.H.: Acoustic parameters in speaker height and weight identification: Sex-specific behaviour. Language and Speech\u00a038(3), 267\u2013287 (1995)","journal-title":"Language and Speech"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Dongdong, L., Yingchun, Y.: Emotional speech clustering based robust speaker recognition system. In: Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP 2009, Tianjin, China, pp. 1\u20135 (2009)","DOI":"10.1109\/CISP.2009.5304327"},{"issue":"1","key":"3_CR24","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1037\/1528-3542.2.1.75","volume":"2","author":"H. Elfenbein","year":"2002","unstructured":"Elfenbein, H., Mandal, M.K., Ambady, N., Harizuka, S.: Cross-Cultural Patterns in Emotion Recognition: Highlighting Design and Analytical Techniques. Emotion\u00a02(1), 75\u201384 (2002)","journal-title":"Emotion"},{"key":"3_CR25","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/BF02253071","volume":"20","author":"H. Ellgring","year":"1996","unstructured":"Ellgring, H., Scherer, K.R.: Vocal Indicators of Mood change in Depression. Journal of Nonverbal Behavior\u00a020, 83\u2013110 (1996)","journal-title":"Journal of Nonverbal Behavior"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Erdem, C.E., Bozkurt, E., Erzin, E., Erdem, A.T.: RANSAC-based training data selection for emotion recognition from spontaneous speech. In: AFFINE 2010 - Proceedings of the 3rd ACM Workshop on Affective Interaction in Natural Environments, Co-located with ACM Multimedia 2010, Florence, Italy, pp. 9\u201314 (2010)","DOI":"10.1145\/1877826.1877831"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Esposito, A., Riviello, M.T.: The cross-modal and cross-cultural processing of affective information. In: Proceeding of the 2011 Conference on Neural Nets WIRN10: Proceedings of the 20th Italian Workshop on Neural Nets, vol.\u00a0226, pp. 301\u2013310 (2011)","DOI":"10.3233\/978-1-60750-692-8-301"},{"issue":"2","key":"3_CR28","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.biopsycho.2005.09.003","volume":"72","author":"S. Evans","year":"2006","unstructured":"Evans, S., Neave, N., Wakelin, D.: Relationships between vocal characteristics and body size and shape in human males: An evolutionary explanation for a deep male voice. Biological Psychology\u00a072(2), 160\u2013163 (2006)","journal-title":"Biological Psychology"},{"key":"3_CR29","unstructured":"Eyben, F., Batliner, A., Schuller, B., Seppi, D., Steidl, S.: Cross-Corpus Classification of Realistic Emotions Some Pilot Experiments. In: Proc. 3rd International Workshop on EMOTION (satellite of LREC): Corpora for Research on Emotion and Affect, Valetta, pp. 77\u201382 (2010)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: openEAR - Introducing the Munich Open-Source Emotion and Affect Recognition Toolkit. In: Proc. ACII, Amsterdam, pp. 576\u2013581 (2009)","DOI":"10.1109\/ACII.2009.5349350"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: openSMILE - The Munich Versatile and Fast Open-Source Audio Feature Extractor. In: Proc. ACM Multimedia, Florence, Italy, pp. 1459\u20131462 (2010)","DOI":"10.1145\/1873951.1874246"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Valstar, M., Gunes, H., Schuller, B., Pantic, M.: String-based audiovisual fusion of behavioural events for the assessment of dimensional affect. In: Proc. 9th International IEEE Conference on Face and Gesture Recognition 2011 (FG 2011), Santa Barbara, CA, pp. 322\u2013329 (2011)","DOI":"10.1109\/FG.2011.5771417"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Gillick, D.: Can conversational word usage be used to predict speaker demographics? In: Proc. of Interspeech, Makuhari, Japan, pp. 1381\u20131384 (2010)","DOI":"10.21437\/Interspeech.2010-421"},{"issue":"3","key":"3_CR34","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1556\/Pollack.4.2009.3.14","volume":"4","author":"Gocs\u00e1l","year":"2009","unstructured":"Gocs\u00e1l: Female listeners\u2019 personality attributions to male speakers: The role of acoustic parameters of speech. Pollack Periodica\u00a04(3), 155\u2013165 (2009)","journal-title":"Pollack Periodica"},{"issue":"2","key":"3_CR35","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/S0095-4470(03)00049-4","volume":"32","author":"J. Gonzalez","year":"2004","unstructured":"Gonzalez, J.: Formant frequencies and body size of speaker: a weak relationship in adult humans. Journal of Phonetics\u00a032(2), 277\u2013287 (2004)","journal-title":"Journal of Phonetics"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.: The WEKA Data Mining Software: An Update. SIGKDD Explorations\u00a011 (2009)","DOI":"10.1145\/1656274.1656278"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Hansen, J., Bou-Ghazale, S.: Getting started with susas: A speech under simulated and actual stress database. In: Proc. EUROSPEECH 1997, Rhodes, Greece, vol.\u00a04, pp. 1743\u20131746 (1997)","DOI":"10.21437\/Eurospeech.1997-494"},{"issue":"3","key":"3_CR38","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1080\/01416200903112292","volume":"31","author":"J. Ipgrave","year":"2009","unstructured":"Ipgrave, J.: The language of friendship and identity: Children\u2019s communication choices in an interfaith exchange. British Journal of Religious Education\u00a031(3), 213\u2013225 (2009)","journal-title":"British Journal of Religious Education"},{"key":"3_CR39","doi-asserted-by":"crossref","unstructured":"Jia, L., Chun, C., Jiajun, B., Mingyu, Y., Jianhua, T.: Speech emotion recognition using an enhanced co-training algorithm. In: Proceedings of the 2007 IEEE International Conference on Multimedia and Expo., ICME 2007, Beijing, China, pp. 999\u20131002 (2007)","DOI":"10.1109\/ICME.2007.4284821"},{"key":"3_CR40","unstructured":"Kleynhans, N.T., Barnard, E.: Language dependence in multilingual speaker verification. In: Proceedings of the 16th Annual Symposium of the Pattern Recognition Association of South Africa, Langebaan, South Africa, pp. 117\u2013122 (November 2005)"},{"key":"3_CR41","doi-asserted-by":"publisher","first-page":"795","DOI":"10.3758\/BRM.41.3.795","volume":"41","author":"J. Krajewski","year":"2009","unstructured":"Krajewski, J., Batliner, A., Golz, M.: Acoustic sleepiness detection: Framework and validation of a speech-adapted pattern recognition approach. Behavior Research Methods\u00a041, 795\u2013804 (2009)","journal-title":"Behavior Research Methods"},{"issue":"6","key":"3_CR42","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1016\/S0022-1031(02)00510-3","volume":"38","author":"R.M. Krauss","year":"2002","unstructured":"Krauss, R.M., Freyberg, R., Morsella, E.: Inferring speakers physical attributes from their voices. Journal of Experimental Social Psychology\u00a038(6), 618\u2013625 (2002)","journal-title":"Journal of Experimental Social Psychology"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Laskowski, K., Ostendorf, M., Schultz, T.: Modeling Vocal Interaction for Text-Independent Participant Characterization in Multi-Party Conversation. In: Proceedings of the 9th SIGdial Workshop on Discourse and Dialogue, Columbus, pp. 148\u2013155 (2008)","DOI":"10.3115\/1622064.1622094"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Lee, C., Mower, E., Busso, C., Lee, S., Narayanan, S.: Emotion recognition using a hierarchical binary decision tree approach. In: Proc. Interspeech, Brighton, pp. 320\u2013323 (2009)","DOI":"10.21437\/Interspeech.2009-105"},{"key":"3_CR45","unstructured":"Levit, M., Huber, R., Batliner, A., N\u00f6th, E.: Use of prosodic speech characteristics for automated detection of alcohol intoxination. In: Bacchiani, M., Hirschberg, J., Litman, D., Ostendorf, M. (eds.) Proc. of the Workshop on Prosody and Speech Recognition 2001, Red Bank, NJ, pp. 103\u2013106 (2001)"},{"issue":"1","key":"3_CR46","first-page":"136","volume":"22","author":"D. Li","year":"2009","unstructured":"Li, D., Wu, Z., Yang, Y.: Speaker recognition based on pitch-dependent affective speech clustering. Moshi Shibie yu Rengong Zhineng\/Pattern Recognition and Artificial Intelligence\u00a022(1), 136\u2013141 (2009)","journal-title":"Moshi Shibie yu Rengong Zhineng\/Pattern Recognition and Artificial Intelligence"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Litman, D., Rotaru, M., Nicholas, G.: Classifying Turn-Level Uncertainty Using Word-Level Prosody. In: Proc. Interspeech, Brighton, UK, pp. 2003\u20132006 (2009)","DOI":"10.21437\/Interspeech.2009-577"},{"key":"3_CR48","first-page":"1","volume-title":"Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009","author":"A. Mahdhaoui","year":"2009","unstructured":"Mahdhaoui, A., Chetouani, M.: A new approach for motherese detection using a semi-supervised algorithm. In: Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009, pp. 1\u20136. IEEE, Grenoble (2009)"},{"key":"3_CR49","series-title":"LNAI","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/978-3-642-11509-7_16","volume-title":"Advances in Nonlinear Speech Processing","author":"A. Mahdhaoui","year":"2010","unstructured":"Mahdhaoui, A., Chetouani, M., Kessous, L.: Time-Frequency Features Extraction for Infant Directed Speech Discrimination. In: Sol\u00e9-Casals, J., Zaiats, V. (eds.) NOLISP 2009. LNCS (LNAI), vol.\u00a05933, pp. 120\u2013127. Springer, Heidelberg (2010)"},{"key":"3_CR50","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1016\/j.specom.2009.01.004","volume":"51","author":"A. Maier","year":"2009","unstructured":"Maier, A., Haderlein, T., Eysholdt, U., Rosanowski, F., Batliner, A., Schuster, M., N\u00f6th, E.: PEAKS - A system for the automatic evaluation of voice and speech disorders. Speech Communication\u00a051, 425\u2013437 (2009)","journal-title":"Speech Communication"},{"key":"3_CR51","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/978-3-540-85483-8_30","volume-title":"Intelligent Virtual Agents","author":"X. Mao","year":"2008","unstructured":"Mao, X., Li, Z., Bao, H.: An Extension of MPML with Emotion Recognition Functions Attached. In: Prendinger, H., Lester, J.C., Ishizuka, M. (eds.) IVA 2008. LNCS (LNAI), vol.\u00a05208, pp. 289\u2013295. Springer, Heidelberg (2008)"},{"key":"3_CR52","doi-asserted-by":"crossref","unstructured":"Metze, F., Batliner, A., Eyben, F., Polzehl, T., Schuller, B., Steidl, S.: Emotion recognition using imperfect speech recognition. In: Proc. Interspeech 2010, Makuhari, Japan, pp. 478\u2013481 (2011)","DOI":"10.21437\/Interspeech.2010-202"},{"key":"3_CR53","doi-asserted-by":"crossref","unstructured":"Mohammadi, G., Vinciarelli, A., Mortillaro, M.: The Voice of Personality: Mapping Nonverbal Vocal Behavior into Trait Attributions. In: Proc. SSPW 2010, Firenze, Italy, pp. 17\u201320 (2010)","DOI":"10.1145\/1878116.1878123"},{"key":"3_CR54","doi-asserted-by":"crossref","unstructured":"Mokhtari, A., Campbell, N.: Speaking style variation and speaker personality. In: Proc. of Speech Prosody, Campinas, Brazil, pp. 601\u2013604 (2008)","DOI":"10.21437\/SpeechProsody.2008-136"},{"issue":"4","key":"3_CR55","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/s10772-010-9064-2","volume":"12","author":"I. Mporas","year":"2009","unstructured":"Mporas, I., Ganchev, T.: Estimation of unknown speakers\u2019 height from speech. International Journal of Speech Technology\u00a012(4), 149\u2013160 (2009)","journal-title":"International Journal of Speech Technology"},{"key":"3_CR56","doi-asserted-by":"crossref","unstructured":"M\u00fcller, C., Wittig, F., Baus, J.: Exploiting Speech for Recognizing Elderly Users to Respond to their Special Needs. In: Proceedings of the Eighth European Conference on Speech Communication and Technology (Eurospeech 2003), Geneva, Switzerland, pp. 1305\u20131308 (2003)","DOI":"10.21437\/Eurospeech.2003-413"},{"key":"3_CR57","doi-asserted-by":"crossref","unstructured":"Omar, M.K., Pelecanos, J.: A novel approach to detecting non-native speakers and their native language. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Dallas, Texas, pp. 4398\u20134401 (2010)","DOI":"10.1109\/ICASSP.2010.5495628"},{"issue":"4","key":"3_CR58","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1016\/j.specom.2009.11.006","volume":"52","author":"S.A. Patil","year":"2010","unstructured":"Patil, S.A., Hansen, J.H.L.: The physiological microphone (pmic): A competitive alternative for speaker assessment in stress detection and speaker verification. Speech Communication\u00a052(4), 327\u2013340 (2010)","journal-title":"Speech Communication"},{"key":"3_CR59","doi-asserted-by":"crossref","unstructured":"Polzehl, T., M\u00f6ller, S., Metze, F.: Automatically assessing personality from speech. In: Proceedings - 2010 IEEE 4th International Conference on Semantic Computing, ICSC 2010, Pittsburgh, PA, pp. 134\u2013140 (2010)","DOI":"10.1109\/ICSC.2010.41"},{"key":"3_CR60","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1111\/j.1439-0310.1993.tb00478.x","volume":"15","author":"R. Provine","year":"1993","unstructured":"Provine, R.: Laughter punctuates speech: linguistic, social and gender contexts of laughter. Ethology\u00a015, 291\u2013298 (1993)","journal-title":"Ethology"},{"issue":"2","key":"3_CR61","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1016\/j.bandc.2004.02.052","volume":"55","author":"N. Reilly","year":"2004","unstructured":"Reilly, N., Cannizzaro, M.S., Harel, B.T., Snyder, P.J.: Feigned depression and feigned sleepiness: A voice acoustical analysis. Brain and Cognition\u00a055(2), 383\u2013386 (2004)","journal-title":"Brain and Cognition"},{"key":"3_CR62","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1017\/CBO9780511596544.007","volume-title":"The Cambridge Handbook of Personality Psychology","author":"R. Reisenzein","year":"2009","unstructured":"Reisenzein, R., Weber, H.: Personality and Emotion. In: Corr, P.J., Matthews, G. (eds.) The Cambridge Handbook of Personality Psychology, pp. 54\u201371. Cambridge University Press, Cambridge (2009)"},{"key":"3_CR63","first-page":"1","volume-title":"Oxford Companion to the Affective Sciences","author":"W. Revelle","year":"2009","unstructured":"Revelle, W., Scherer, K.: Personality and Emotion. In: Oxford Companion to the Affective Sciences, pp. 1\u20134. Oxford University Press, Oxford (2009)"},{"key":"3_CR64","doi-asserted-by":"crossref","unstructured":"Ringeval, F., Chetouani, M.: A vowel based approach for acted emotion recognition. In: INTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association, Brisbane, Australia, pp. 2763\u20132766 (2008)","DOI":"10.21437\/Interspeech.2008-685"},{"key":"3_CR65","doi-asserted-by":"crossref","unstructured":"Rosenberg, A., Hirschberg, J.: Acoustic\/Prosodic and Lexical Correlates of Charismatic Speech. In: Proc. of Interspeech, Lisbon, pp. 513\u2013516 (2005)","DOI":"10.21437\/Interspeech.2005-329"},{"key":"3_CR66","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1037\/h0077714","volume":"39","author":"J.A. Russel","year":"1980","unstructured":"Russel, J.A.: A circumplex model of affect. Journal of Personality and Social Psychology\u00a039, 1161\u20131178 (1980)","journal-title":"Journal of Personality and Social Psychology"},{"issue":"6","key":"3_CR67","doi-asserted-by":"publisher","first-page":"2408","DOI":"10.1073\/pnas.0908239106","volume":"107","author":"D.A. Sauter","year":"2010","unstructured":"Sauter, D.A., Eisner, F., Ekman, P., Scott, S.K.: Cross-cultural recognition of basic emotions through nonverbal emotional vocalizations. Proc. of the National Academy of Sciences of the U.S.A.\u00a0107(6), 2408\u20132412 (2010)","journal-title":"Proc. of the National Academy of Sciences of the U.S.A."},{"key":"3_CR68","doi-asserted-by":"crossref","unstructured":"Schiel, F., Heinrich, C.: Laying the foundation for in-car alcohol detection by speech. In: Proc. INTERSPEECH 2009, Brighton, UK, pp. 983\u2013986 (2009)","DOI":"10.21437\/Interspeech.2009-292"},{"key":"3_CR69","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1007\/978-3-540-74889-2_39","volume-title":"Affective Computing and Intelligent Interaction","author":"M. Schr\u00f6der","year":"2007","unstructured":"Schr\u00f6der, M., Devillers, L., Karpouzis, K., Martin, J.-C., Pelachaud, C., Peter, C., Pirker, H., Schuller, B., Tao, J., Wilson, I.: What Should a Generic Emotion Markup Language Be Able to Represent? In: Paiva, A.C.R., Prada, R., Picard, R.W. (eds.) ACII 2007. LNCS, vol.\u00a04738, pp. 440\u2013451. Springer, Heidelberg (2007)"},{"issue":"2","key":"3_CR70","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s10772-011-9090-8","volume":"14","author":"B. Schuller","year":"2011","unstructured":"Schuller, B.: Affective speaker state analysis in the presence of reverberation. International Journal of Speech Technology\u00a014(2), 77\u201387 (2011)","journal-title":"International Journal of Speech Technology"},{"key":"3_CR71","doi-asserted-by":"crossref","unstructured":"Schuller, B., Batliner, A., Steidl, S., Seppi, D.: Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge. Speech Communication 53, Special Issue on Sensing Emotion and Affect - Facing Realism in Speech Processing (9\/10), 1062\u20131087 (2011)","DOI":"10.1016\/j.specom.2011.01.011"},{"key":"3_CR72","doi-asserted-by":"crossref","unstructured":"Schuller, B., Burkhardt, F.: Learning with Synthesized Speech for Automatic Emotion Recognition. In: Proc. 35th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Dallas, pp. 5150\u20135153 (2010)","DOI":"10.1109\/ICASSP.2010.5495017"},{"key":"3_CR73","doi-asserted-by":"crossref","unstructured":"Schuller, B., Jim\u00e9nez Villar, R., Rigoll, G., Lang, M.: Meta-classifiers in acoustic and linguistic feature fusion-based affect recognition. In: Proc. ICASSP, Philadelphia, pp. I:325\u2013I:328 (2005)","DOI":"10.1109\/ICASSP.2005.1415116"},{"key":"3_CR74","doi-asserted-by":"crossref","unstructured":"Schuller, B., Reiter, S., Rigoll, G.: Evolutionary feature generation in speech emotion recognition. In: Proc. Int. Conf. on Multimedia and Expo, ICME 2006, Toronto, Canada, pp. 5\u20138 (2006)","DOI":"10.1109\/ICME.2006.262500"},{"key":"3_CR75","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: Proc. ICASSP, Montreal, pp. 577\u2013580 (2004)","DOI":"10.1109\/ICASSP.2004.1326051"},{"key":"3_CR76","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., Batliner, A.: The INTERSPEECH 2009 Emotion Challenge. In: Proceedings of 11th European Conference on Speech Communication and Technology, Interspeech 2009 \u2013 Eurospeech, Brighton, UK, September 6-10, pp. 312\u2013315 (2009)","DOI":"10.21437\/Interspeech.2009-103"},{"key":"3_CR77","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., Batliner, A., Burkhardt, F., Devillers, L., M\u00fcller, C., Narayanan, S.: The INTERSPEECH 2010 Paralinguistic Challenge \u2013 Age, Gender, and Affect. In: Proceedings of 11th International Conference on Spoken Language Processing, Interspeech 2010 \u2013 ICSLP, Makuhari, Japan, September 26-30, pp. 2794\u20132797 (2010)","DOI":"10.21437\/Interspeech.2010-739"},{"key":"3_CR78","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., Batliner, A., Schiel, F., Krajewski, J.: The Interspeech 2011 Speaker State Challenge. In: Proc. Interspeech, Florence, Italy, pp. 3201\u20133204 (2011)","DOI":"10.21437\/Interspeech.2011-801"},{"issue":"2","key":"3_CR79","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1109\/T-AFFC.2010.8","volume":"1","author":"B. Schuller","year":"2010","unstructured":"Schuller, B., Vlasenko, B., Eyben, F., W\u00f6llmer, M., Stuhlsatz, A., Wendemuth, A., Rigoll, G.: Cross-corpus acoustic emotion recognition: Variances and strategies. IEEE Transactions on Affective Computing\u00a01(2), 119\u2013131 (2010)","journal-title":"IEEE Transactions on Affective Computing"},{"key":"3_CR80","doi-asserted-by":"crossref","unstructured":"Schuller, B., Wimmer, M., M\u00f6senlechner, L., Kern, C., Arsic, D., Rigoll, G.: Brute-Forcing Hierarchical Functionals for Paralinguistics: a Waste of Feature Space? In: Proc. ICASSP, Las Vegas, pp. 4501\u20134504 (2008)","DOI":"10.1109\/ICASSP.2008.4518656"},{"key":"3_CR81","unstructured":"Schuller, B., W\u00f6llmer, M., Eyben, F., Rigoll, G., Arsic, D.: Semantic Speech Tagging: Towards Combined Analysis of Speaker Traits. In: Proc. AES 42nd International Conference, Ilmenau, Germany, pp. 89\u201397 (2011)"},{"key":"3_CR82","unstructured":"Schuller, B., Zhang, Z., Weninger, F., Rigoll, G.: Selecting training data for cross-corpus speech emotion recognition: Prototypicality vs. generalization. In: Proc. 2011 Afeka-AVIOS Speech Processing Conference, Tel Aviv, Israel (2011)"},{"key":"3_CR83","doi-asserted-by":"publisher","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.: Being Bored? Recognising Natural Interest by Extensive Audiovisual Integration for Real-Life Application. Image and Vision Computing Journal, Special Issue on Visual and Multimodal Analysis of Human Spontaneous Behavior\u00a027, 1760\u20131774 (2009)","journal-title":"Image and Vision Computing Journal, Special Issue on Visual and Multimodal Analysis of Human Spontaneous Behavior"},{"key":"3_CR84","unstructured":"Schuller, B., Steidl, S., Batliner, A., Burkhardt, F., Devillers, L., M\u00fcller, C., Narayanan, S.: Paralinguistics in Speech and Language\u2014State-of-the-Art and the Challenge. Computer Speech and Language, Special Issue on Paralinguistics in Naturalistic Speech and Language (2011) (to appear)"},{"key":"3_CR85","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.21437\/Interspeech.2011-468","volume-title":"Proc. of INTERSPEECH","author":"B. Schuller","year":"2011","unstructured":"Schuller, B., Zhang, Z., Weninger, F., Rigoll, G.: Using Multiple Databases for Training in Emotion Recognition: To Unite or to Vote? In: Proc. of INTERSPEECH, pp. 1553\u20131556. ISCA, Florence (2011)"},{"key":"3_CR86","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/978-3-642-12127-2_33","volume-title":"Multiple Classifier Systems","author":"F. Schwenker","year":"2010","unstructured":"Schwenker, F., Scherer, S., Schmidt, M., Schels, M., Glodek, M.: Multiple Classifier Systems for the Recogonition of Human Emotions. In: El Gayar, N., Kittler, J., Roli, F. (eds.) MCS 2010. LNCS, vol.\u00a05997, pp. 315\u2013324. Springer, Heidelberg (2010)"},{"key":"3_CR87","doi-asserted-by":"crossref","unstructured":"Shahin, I.: Verifying speakers in emotional environments. In: IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2009, Ajman, UAE, pp. 328\u2013333 (2009)","DOI":"10.1109\/ISSPIT.2009.5407568"},{"key":"3_CR88","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/978-3-540-74122-0_5","volume-title":"Speaker Classification II: Selected Projects","author":"M. Shami","year":"2007","unstructured":"Shami, M., Verhelst, W.: Automatic classification of expressiveness in speech: A multi-corpus study. In: Mueller, C. (ed.) Speaker Classification II: Selected Projects, pp. 43\u201356. Springer, Berlin (2007)"},{"key":"3_CR89","doi-asserted-by":"crossref","first-page":"2993","DOI":"10.21437\/Interspeech.2005-137","volume-title":"Proc. of Interspeech 2005","author":"J. Stadermann","year":"2005","unstructured":"Stadermann, J., Koska, W., Rigoll, G.: Multi-task learning strategies for a recurrent neural net in a hybrid tied-posteriors acoustic mode. In: Proc. of Interspeech 2005, pp. 2993\u20132996. ISCA, Lisbon (2005)"},{"key":"3_CR90","doi-asserted-by":"crossref","unstructured":"Steidl, S., Schuller, B., Batliner, A., Seppi, D.: The Hinterland of Emotions: Facing the Open-Microphone Challenge. In: Proc. ACII, Amsterdam, pp. 690\u2013697 (2009)","DOI":"10.1109\/ACII.2009.5349499"},{"key":"3_CR91","doi-asserted-by":"crossref","unstructured":"Stuhlsatz, A., Meyer, C., Eyben, F., Zielke, T., Meier, G., Schuller, B.: Deep Neural Networks for Acoustic Emotion Recognition: Raising the Benchmarks. In: Proc. ICASSP, Prague, Czech Republic, pp. 5688\u20135691 (2011)","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"3_CR92","doi-asserted-by":"crossref","unstructured":"Tabatabaei, T.S., Krishnan, S.: Towards robust speech-based emotion recognition. In: Proc. IEEE International Conference on Systems, Man and Cybernetics, Istanbul, Turkey, pp. 608\u2013611 (2010)","DOI":"10.1109\/ICSMC.2010.5641815"},{"key":"3_CR93","unstructured":"Ververidis, D., Kotropoulos, C.: Automatic speech classification to five emotional states based on gender information. In: Proc. of 12th European Signal Processing Conference, Vienna, Austria, pp. 341\u2013344 (2004)"},{"key":"3_CR94","doi-asserted-by":"publisher","first-page":"1743","DOI":"10.1016\/j.imavis.2008.11.007","volume":"27","author":"A. Vinciarelli","year":"2009","unstructured":"Vinciarelli, A., Pantic, M., Bourlard, H.: Social signal processing: Survey of an emerging domain. Image and Vision Computing\u00a027, 1743\u20131759 (2009)","journal-title":"Image and Vision Computing"},{"key":"3_CR95","unstructured":"Vogt, T., Andre, E.: Improving automatic emotion recognition from speech via gender differentiation. In: Proc. of Language Resources and Evaluation Conference (LREC 2006), Genoa, Italy, pp. 1\u20134 (2006)"},{"key":"3_CR96","doi-asserted-by":"crossref","unstructured":"Weninger, F., Schuller, B., Batliner, A., Steidl, S., Seppi, D.: Recognition of nonprototypical emotions in reverberated and noisy speech by nonnegative matrix factorization. Eurasip Journal on Advances in Signal Processing 2011(Article ID 838790), 16 pages (2011)","DOI":"10.1155\/2011\/838790"},{"issue":"5","key":"3_CR97","doi-asserted-by":"publisher","first-page":"867","DOI":"10.1109\/JSTSP.2010.2057200","volume":"4","author":"M. W\u00f6llmer","year":"2010","unstructured":"W\u00f6llmer, M., Schuller, B., Eyben, F., Rigoll, G.: Combining long short-term memory and dynamic bayesian networks for incremental emotion-sensitive artificial listening. IEEE Journal of Selected Topics in Signal Processing\u00a04(5), 867\u2013881 (2010)","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"3_CR98","doi-asserted-by":"crossref","unstructured":"W\u00f6llmer, M., Weninger, F., Eyben, F., Schuller, B.: Acoustic-Linguistic Recognition of Interest in Speech with Bottleneck-BLSTM Nets. In: Proc. of INTERSPEECH, Florence, Italy, pp. 77\u201380 (2011)","DOI":"10.21437\/Interspeech.2011-20"},{"issue":"5","key":"3_CR99","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1016\/j.specom.2010.08.013","volume":"53","author":"S. Wu","year":"2011","unstructured":"Wu, S., Falk, T.H., Chan, W.: Automatic speech emotion recognition using modulation spectral features. Speech Communication\u00a053(5), 768\u2013785 (2011)","journal-title":"Speech Communication"},{"issue":"8","key":"3_CR100","doi-asserted-by":"publisher","first-page":"2353","DOI":"10.1016\/j.sigpro.2009.06.001","volume":"90","author":"M. Yamada","year":"2010","unstructured":"Yamada, M., Sugiyama, M., Matsui, T.: Semi-supervised speaker identification under covariate shift. Signal Processing\u00a090(8), 2353\u20132361 (2010)","journal-title":"Signal Processing"},{"key":"3_CR101","doi-asserted-by":"crossref","unstructured":"Yoon, W., Park, K.: Building robust emotion recognition system on heterogeneous speech databases. In: Digest of Technical Papers - IEEE International Conference on Consumer Electronics, pp. 825\u2013826 (2011)","DOI":"10.1109\/ICCE.2011.5722886"},{"key":"3_CR102","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Singh, V., Slowe, T., Tulyakov, S., Govindaraju, V.: Real-time Automatic Deceit Detection from Involuntary Facial Expressions. In: Proc. of CVPR, pp. 1\u20136 (2007)","DOI":"10.1109\/CVPR.2007.383383"},{"key":"3_CR103","volume-title":"Proc. Automatic Speech Recognition and Understanding Workshop (ASRU 2011)","author":"Z. Zhang","year":"2011","unstructured":"Zhang, Z., Weninger, F., W\u00f6llmer, M., Schuller, B.: Unsupervised Learning in Cross-Corpus Acoustic Emotion Recognition. In: Proc. Automatic Speech Recognition and Understanding Workshop (ASRU 2011). IEEE, Big Island (2011)"}],"container-title":["Lecture Notes in Computer Science","Cognitive Behavioural Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-34584-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T01:01:00Z","timestamp":1745197260000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-34584-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642345838","9783642345845"],"references-count":103,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-34584-5_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}