{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:15:21Z","timestamp":1776888921035,"version":"3.51.2"},"reference-count":88,"publisher":"Springer Science and Business Media LLC","issue":"7-8","license":[{"start":{"date-parts":[[2013,3,29]],"date-time":"2013-03-29T00:00:00Z","timestamp":1364515200000},"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":[[2014,6]]},"DOI":"10.1007\/s00521-013-1377-z","type":"journal-article","created":{"date-parts":[[2013,3,28]],"date-time":"2013-03-28T05:54:25Z","timestamp":1364450065000},"page":"1539-1553","source":"Crossref","is-referenced-by-count":40,"title":["Robust emotion recognition in noisy speech via sparse representation"],"prefix":"10.1007","volume":"24","author":[{"given":"Xiaoming","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiqing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bicheng","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,3,29]]},"reference":[{"key":"1377_CR1","doi-asserted-by":"crossref","DOI":"10.1037\/e526112012-054","volume-title":"Affective computing","author":"R Picard","year":"1997","unstructured":"Picard R (1997) Affective computing. MIT Press, Cambridge"},{"issue":"1","key":"1377_CR2","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/79.911197","volume":"18","author":"R Cowie","year":"2001","unstructured":"Cowie R, Douglas-Cowie E, Tsapatsoulis N, Votsis G, Kollias S, Fellenz W, Taylor JG (2001) Emotion recognition in human-computer interaction. IEEE Signal Process Mag 18(1):32\u201380","journal-title":"IEEE Signal Process Mag"},{"issue":"2","key":"1377_CR3","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/TSA.2004.838534","volume":"13","author":"CM Lee","year":"2005","unstructured":"Lee CM, Narayanan SS (2005) Toward detecting emotions in spoken dialogs. IEEE Trans Speech Audio Process 13(2):293\u2013303","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"4","key":"1377_CR4","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1109\/TASL.2008.2009578","volume":"17","author":"C Busso","year":"2009","unstructured":"Busso C, Sungbok L, Narayanan S (2009) Analysis of emotionally salient aspects of fundamental frequency for emotion detection. IEEE Trans Audio Speech Lang Process 17(4):582\u2013596","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"6","key":"1377_CR5","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1109\/TMM.2010.2051872","volume":"12","author":"I Luengo","year":"2010","unstructured":"Luengo I, Navas E, Hernaez I (2010) Feature analysis and evaluation for automatic emotion identification in speech. IEEE Trans Multimedia 12(6):490\u2013501","journal-title":"IEEE Trans Multimedia"},{"issue":"3","key":"1377_CR6","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1016\/j.specom.2004.09.010","volume":"47","author":"C Dromey","year":"2005","unstructured":"Dromey C, Silveira J, Sandor P (2005) Recognition of affective prosody by speakers of English as a first or foreign language. Speech Commun 47(3):351\u2013359","journal-title":"Speech Commun"},{"issue":"1","key":"1377_CR7","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, Amir N, Kessous L, Aharonson V (2011) Whodunnit: searching for the most important feature types signalling emotion-related user states in speech. Comput Speech Lang 25(1):4\u201328","journal-title":"Comput Speech Lang"},{"issue":"1","key":"1377_CR8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.specom.2011.05.011","volume":"54","author":"A Jaywant","year":"2012","unstructured":"Jaywant A, Pell MD (2012) Categorical processing of negative emotions from speech prosody. Speech Commun 54(1):1\u201310","journal-title":"Speech Commun"},{"issue":"3","key":"1377_CR9","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M Ayadi El","year":"2010","unstructured":"El Ayadi M, Kamel M, Karray F (2010) Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recogn 44(3):572\u2013587","journal-title":"Pattern Recogn"},{"key":"1377_CR10","unstructured":"Gharavian D, Sheikhan M, Nazerieh A, Garoucy S (2011) Speech emotion recognition using FCBF feature selection method and GA-optimized fuzzy ARTMAP neural network. Neural Comput Appl. Article (in press). doi: 10.1007\/s00521-00011-00643-00521"},{"issue":"1\u20132","key":"1377_CR11","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/S0167-6393(02)00082-1","volume":"40","author":"C Gobl","year":"2003","unstructured":"Gobl C, Chasaide AN (2003) The role of voice quality in communicating emotion, mood and attitude. Speech Commun 40(1\u20132):189\u2013212","journal-title":"Speech Commun"},{"key":"1377_CR12","doi-asserted-by":"crossref","unstructured":"Zhang S (2008) Emotion recognition in Chinese natural speech by combining prosody and voice quality features. In: Advances in neural networks\u2014ISNN 2008, Lecture Notes in Computer Science 5264, vol 5264. Springer, pp 457\u2013464","DOI":"10.1007\/978-3-540-87734-9_52"},{"key":"1377_CR13","doi-asserted-by":"crossref","unstructured":"Schuller B, Batliner A, Seppi D, Steidl S, Vogt T, Wagner J, Devillers L, Vidrascu L, Amir N, Kessous L (2007) The relevance of feature type for the automatic classification of emotional user states: low level descriptors and functionals. In: INTERSPEECH-2007, Antwerp, Belgium, pp 2253\u20132256","DOI":"10.21437\/Interspeech.2007-612"},{"issue":"4","key":"1377_CR14","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1016\/S0167-6393(03)00099-2","volume":"41","author":"TL Nwe","year":"2003","unstructured":"Nwe TL, Foo SW, De Silva LC (2003) Speech emotion recognition using hidden Markov models. Speech Commun 41(4):603\u2013623","journal-title":"Speech Commun"},{"key":"1377_CR15","first-page":"92","volume-title":"Acoustical analysis of spectral and temporal changes in emotional speech","author":"M Kienast","year":"2000","unstructured":"Kienast M, Sendlmeier W (2000) Acoustical analysis of spectral and temporal changes in emotional speech. ITRW on speech and emotion, Newcastle, pp 92\u201397"},{"issue":"7\u20138","key":"1377_CR16","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(7\u20138):613\u2013625","journal-title":"Speech Commun"},{"issue":"7","key":"1377_CR17","doi-asserted-by":"crossref","first-page":"1765","DOI":"10.1007\/s00521-011-0620-8","volume":"21","author":"M Sheikhan","year":"2012","unstructured":"Sheikhan M, Gharavian D, Ashoftedel F (2012) Using DTW neural\u2013based MFCC warping to improve emotional speech recognition. Neural Comput Appl 21(7):1765\u20131773","journal-title":"Neural Comput Appl"},{"key":"1377_CR18","doi-asserted-by":"crossref","unstructured":"Hu H, Xu MX, Wu W (2007) GMM supervector based SVM with spectral features for speech emotion recognition. In: IEEE international conference on acoustics, speech, and signal processing (ICASSP\u201907), Honolulu, HI, pp 413\u2013416","DOI":"10.1109\/ICASSP.2007.366937"},{"issue":"6","key":"1377_CR19","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1109\/TMM.2010.2058095","volume":"12","author":"A Tawari","year":"2010","unstructured":"Tawari A, Trivedi MM (2010) Speech emotion analysis: exploring the role of context. IEEE Trans Multimedia 12(6):502\u2013509","journal-title":"IEEE Trans Multimedia"},{"issue":"1","key":"1377_CR20","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.csl.2009.12.004","volume":"25","author":"S Yildirim","year":"2011","unstructured":"Yildirim S, Narayanan S, Potamianos A (2011) Detecting emotional state of a child in a conversational computer game. Comput Speech Lang 25(1):29\u201344","journal-title":"Comput Speech Lang"},{"key":"1377_CR21","doi-asserted-by":"crossref","unstructured":"Schuller B, Batliner A, Steidl S, Seppi D (2009) Emotion recognition from speech: putting ASR in the loop. In: IEEE international conference on acoustics, speech and signal processing (ICASSP), Taipei, pp 4585\u20134588","DOI":"10.1109\/ICASSP.2009.4960651"},{"issue":"5","key":"1377_CR22","doi-asserted-by":"crossref","first-page":"5115","DOI":"10.1016\/j.eswa.2011.11.028","volume":"39","author":"N Kamaruddin","year":"2012","unstructured":"Kamaruddin N, Wahab A, Quek C (2012) Cultural dependency analysis for understanding speech emotion. Expert Syst Appl 39(5):5115\u20135133","journal-title":"Expert Syst Appl"},{"issue":"2","key":"1377_CR23","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.specom.2006.11.004","volume":"49","author":"D Morrison","year":"2007","unstructured":"Morrison D, Wang R, De Silva LC (2007) Ensemble methods for spoken emotion recognition in call-centres. Speech Commun 49(2):98\u2013112","journal-title":"Speech Commun"},{"issue":"3","key":"1377_CR24","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 Y-PP (2009) Acoustic feature selection for automatic emotion recognition from speech. Inf Process Manage 45(3):315\u2013328","journal-title":"Inf Process Manage"},{"key":"1377_CR25","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-1904-8","volume-title":"Principal component analysis","author":"IT Jolliffe","year":"1986","unstructured":"Jolliffe IT (1986) Principal component analysis, 2nd edn. Springer, Berlin","edition":"2"},{"key":"1377_CR26","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1111\/j.1469-1809.1936.tb02137.x","volume":"7","author":"R Fisher","year":"1936","unstructured":"Fisher R (1936) The use of multiple measures in taxonomic problems. Ann Eugenics 7:179\u2013188","journal-title":"Ann Eugenics"},{"key":"1377_CR27","doi-asserted-by":"crossref","unstructured":"Lee CM, Narayanan SS, Pieraccini R (2001) Recognition of negative emotions from the speech signal. In: IEEE Workshop automatic speech recognition and understanding (ASRU), Trento, pp 240\u2013243","DOI":"10.1109\/ASRU.2001.1034632"},{"issue":"5500","key":"1377_CR28","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","volume":"290","author":"ST Roweis","year":"2000","unstructured":"Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323\u20132326","journal-title":"Science"},{"issue":"5500","key":"1377_CR29","doi-asserted-by":"crossref","first-page":"2319","DOI":"10.1126\/science.290.5500.2319","volume":"290","author":"JB Tenenbaum","year":"2000","unstructured":"Tenenbaum JB, Silva Vd, Langford JC (2000) A global geometric framework for nonlinear dimensionality reduction. Science 290(5500):2319\u20132323","journal-title":"Science"},{"issue":"1","key":"1377_CR30","first-page":"49","volume":"12","author":"M You","year":"2007","unstructured":"You M, Chen C, Bu J, Liu J, Tao J (2007) Manifolds based emotion recognition in speech. Comput Linguist Chin Lang Process 12(1):49\u201364","journal-title":"Comput Linguist Chin Lang Process"},{"key":"1377_CR31","unstructured":"Zhang S, Zhao X (2011) Dimensionality reduction-based spoken emotion recognition. Multimedia tools and applications: Article (in press). doi: 10.1007\/s11042-11011-10887-x"},{"key":"1377_CR32","unstructured":"Petrushin V (1999) Emotion in speech: recognition and application to call centers. In: 1999 Artificial neural networks in engineering (ANNIE \u201899), New York, pp 7\u201310"},{"key":"1377_CR33","doi-asserted-by":"crossref","unstructured":"Dellaert F, Polzin T, Waibel A (1996) Recognizing emotion in speech. In: 4th International conference on spoken language processing (ICSLP\u201996), Philadelphia, pp 1970\u20131973","DOI":"10.1109\/ICSLP.1996.608022"},{"issue":"4","key":"1377_CR34","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1007\/s005210070006","volume":"9","author":"J Nicholson","year":"2000","unstructured":"Nicholson J, Takahashi K, Nakatsu R (2000) Emotion recognition in speech using neural networks. Neural Comput Appl 9(4):290\u2013296","journal-title":"Neural Comput Appl"},{"key":"1377_CR35","doi-asserted-by":"crossref","unstructured":"Petrushin V (2000) Emotion recognition in speech signal: experimental study, development, and application. In: 6th International conference on spoken language processing (ICSLP\u201900), Beijing, pp 222\u2013225","DOI":"10.21437\/ICSLP.2000-791"},{"key":"1377_CR36","doi-asserted-by":"crossref","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 (ICASSP), Montreal, Quebec, Canada, pp 577\u2013580","DOI":"10.1109\/ICASSP.2004.1326051"},{"key":"1377_CR37","doi-asserted-by":"crossref","unstructured":"Kwon O, Chan K, Hao J, Lee T (2003) Emotion recognition by speech signals. In: EUROSPEECH-2003, Geneva, Switzerland, pp 125\u2013128","DOI":"10.21437\/Eurospeech.2003-80"},{"issue":"4","key":"1377_CR38","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(4):8197\u20138203","journal-title":"Expert Syst Appl"},{"key":"1377_CR39","unstructured":"Sheikhan M, Bejani M, Gharavian D (2012) Modular neural-SVM scheme for speech emotion recognition using ANOVA feature selection method. Neural Comput Appl. Article (in press). doi: 10.1007\/s00521-00012-00814-00528"},{"key":"1377_CR40","doi-asserted-by":"crossref","unstructured":"Ververidis D, Kotropoulos C (2005) Emotional speech classification using Gaussian mixture models. In: IEEE international conference on multimedia and expo (ICME\u201905), Amsterdam, The Netherlands, pp 2871\u20132874","DOI":"10.1109\/ISCAS.2005.1465226"},{"key":"1377_CR41","doi-asserted-by":"crossref","unstructured":"Iliev A, Zhang Y, Scordilis M (2007) Spoken Emotion Classification Using ToBI Features and GMM. In: IEEE 6th EURASIP conference focused on speech and image processing, Maribor, Slovenia, pp 495\u2013498","DOI":"10.1109\/IWSSIP.2007.4381149"},{"key":"1377_CR42","doi-asserted-by":"crossref","unstructured":"Lee C, Yildirim S, Bulut M, Kazemzadeh A, Busso C, Deng Z, Lee S, Narayanan S (2004) Emotion recognition based on phoneme classes. In: International conference on spoken language processing (ICSLP\u201904), Jeju, Korea, pp 889\u2013892","DOI":"10.21437\/Interspeech.2004-322"},{"issue":"9\u201310","key":"1377_CR43","first-page":"1162","volume":"53","author":"CC Lee","year":"2011","unstructured":"Lee CC, Mower E, Busso C, Lee S, Narayanan S (2011) Emotion recognition using a hierarchical binary decision tree approach. Speech Commun 53(9\u201310):1162\u20131171","journal-title":"Speech Commun"},{"issue":"3","key":"1377_CR44","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(3):556\u2013570","journal-title":"Comput Speech Lang"},{"issue":"9","key":"1377_CR45","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":"3","key":"1377_CR46","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.specom.2007.01.006","volume":"49","author":"M Shami","year":"2007","unstructured":"Shami M, Verhelst W (2007) An evaluation of the robustness of existing supervised machine learning approaches to the classification of emotions in speech. Speech Commun 49(3):201\u2013212","journal-title":"Speech Commun"},{"key":"1377_CR47","doi-asserted-by":"crossref","unstructured":"Schuller B, Arsic D, Wallhoff F, Rigoll G (2006) Emotion recognition in the noise applying large acoustic feature sets. In: Speech Prosody, Dresden, Germany","DOI":"10.21437\/SpeechProsody.2006-150"},{"key":"1377_CR48","doi-asserted-by":"crossref","unstructured":"You M, Chen C, Bu J, Liu J, Tao J (2006) Emotion recognition from noisy speech. In: IEEE international conference on multimedia and expo (ICME\u201906), Toronto, Ont, pp 1653\u20131656","DOI":"10.1109\/ICME.2006.262865"},{"issue":"10\u201312","key":"1377_CR49","doi-asserted-by":"crossref","first-page":"1913","DOI":"10.1016\/j.neucom.2007.07.041","volume":"71","author":"M Song","year":"2008","unstructured":"Song M, You M, Li N, Chen C (2008) A robust multimodal approach for emotion recognition. Neurocomputing 71(10\u201312):1913\u20131920","journal-title":"Neurocomputing"},{"key":"1377_CR50","doi-asserted-by":"crossref","unstructured":"Yeh L, Chi T (2010) Spectro-temporal modulations for robust speech emotion recognition. In: INTERSPEECH-2010, Makuhari, Chiba, Japan, pp 789\u2013792","DOI":"10.21437\/Interspeech.2010-286"},{"issue":"4","key":"1377_CR51","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1109\/TIT.2006.871582","volume":"52","author":"DL Donoho","year":"2006","unstructured":"Donoho DL (2006) Compressed sensing. IEEE Trans Inf Theory 52(4):1289\u20131306","journal-title":"IEEE Trans Inf Theory"},{"issue":"4","key":"1377_CR52","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1109\/MSP.2007.4286571","volume":"24","author":"RG Baraniuk","year":"2007","unstructured":"Baraniuk RG (2007) Compressive sensing [lecture notes]. IEEE Signal Process Mag 24(4):118\u2013121","journal-title":"IEEE Signal Process Mag"},{"issue":"2","key":"1377_CR53","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/MSP.2007.914731","volume":"25","author":"EJ Candes","year":"2008","unstructured":"Candes EJ, Wakin MB (2008) An introduction to compressive sampling. IEEE Signal Process Mag 25(2):21\u201330","journal-title":"IEEE Signal Process Mag"},{"issue":"2","key":"1377_CR54","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1109\/TPAMI.2008.79","volume":"31","author":"J Wright","year":"2009","unstructured":"Wright J, Yang AY, Ganesh A, Sastry SS, Ma Y (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31(2):210\u2013227","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"1377_CR55","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1109\/JPROC.2010.2044470","volume":"98","author":"J Wright","year":"2010","unstructured":"Wright J, Ma Y, Mairal J, Sapiro G, Huang TS, Yan S (2010) Sparse representation for computer vision and pattern recognition. Proc IEEE 98(6):1031\u20131044","journal-title":"Proc IEEE"},{"key":"1377_CR56","first-page":"1","volume":"99","author":"A Wagner","year":"2011","unstructured":"Wagner A, Wright J, Ganesh A, Zhou Z, Mobahi H, Ma Y (2011) Towards a practical face recognition system: robust alignment and illumination by sparse representation. IEEE Trans Pattern Anal Mach Intell 99:1\u201315","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1377_CR57","doi-asserted-by":"crossref","unstructured":"Sainath TN, Ramabhadran B, Nahamoo D, Kanevsky D, Sethy A (2010) Sparse representation features for speech recognition. In: INTERSPEECH-2010, Makuhari, Chiba, Japan, pp 2254\u20132257","DOI":"10.21437\/Interspeech.2010-619"},{"issue":"7","key":"1377_CR58","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1109\/TASL.2011.2112350","volume":"19","author":"J Gemmeke","year":"2011","unstructured":"Gemmeke J, Virtanen T, Hurmalainen A (2011) Exemplar-based sparse representations for noise robust automatic speech recognition. IEEE Trans Audio Speech Lang Process 19(7):2067\u20132080","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"1377_CR59","unstructured":"Candes E, Romberg J (2005) l1-magic: recovery of sparse signals via convex programming. Available at http:\/\/users.ece.gatech.edu\/justin\/l1magic\/downloads\/l1magic.pdf"},{"issue":"4","key":"1377_CR60","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1109\/JSTSP.2007.910971","volume":"1","author":"SJ Kim","year":"2007","unstructured":"Kim SJ, Koh K, Lustig M, Boyd S, Gorinevsky D (2007) An interior-point method for large-scale l1-regularized least squares. IEEE J Select Top Signal Process 1(4):606\u2013617","journal-title":"IEEE J Select Top Signal Process"},{"key":"1377_CR61","doi-asserted-by":"crossref","unstructured":"Tibshirani R (1996) Regression shrinkage and selection via the lasso. J Roy Stat Soc Ser B (Methodological):267\u2013288","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"1377_CR62","doi-asserted-by":"crossref","unstructured":"Burkhardt F, Paeschke A, Rolfes M, Sendlmeier W, Weiss B (2005) A database of German emotional speech. In: Interspeech-2005, Lisbon, Portugal, pp 1\u20134","DOI":"10.21437\/Interspeech.2005-446"},{"key":"1377_CR63","unstructured":"CICHOSZ J, SLOT K (2005) Application of selected speech-signal characteristics to emotion recognition in polish language. In: International conference on signals and electronic systems, Poznan, Poland, pp 409\u2013412"},{"key":"1377_CR64","doi-asserted-by":"crossref","unstructured":"Batliner A, Buckow A, Niemann H, Noth E, Warnke V (2000) The prosody module. VERBMOBIL: foundations of speech-to-speech translations: 106\u2013121","DOI":"10.1007\/978-3-662-04230-4_8"},{"key":"1377_CR65","doi-asserted-by":"crossref","unstructured":"Ang J, Dhillon R, Krupski A, Shriberg E, Stolcke A (2002) Prosody-based automatic detection of annoyance and frustration in human-computer dialog. In: 7th international conference on spoken language processing (ICSLP\u201902), Denver, Colorado, pp 2037\u20132040","DOI":"10.21437\/ICSLP.2002-559"},{"key":"1377_CR66","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1121\/1.405558","volume":"93","author":"I Murray","year":"1993","unstructured":"Murray I, Arnott J (1993) Toward the simulation of emotion in synthetic speech: a review of the literature on human vocal emotion. J Acoust Soc Am 93:1097\u20131108","journal-title":"J Acoust Soc Am"},{"key":"1377_CR67","first-page":"97","volume":"17","author":"P Boersma","year":"1993","unstructured":"Boersma P (1993) Accurate short-term analysis of the fundamental frequency and the harmonics-to-noise ratio of a sampled sound. Proc Inst Phon Sci 17:97\u2013110","journal-title":"Proc Inst Phon Sci"},{"key":"1377_CR68","unstructured":"McGilloway S, Cowie R, Douglas-Cowie E, Gielen S, Westerdijk M, Stroeve S (2000) Approaching automatic recognition of emotion from voice: a rough benchmark. In: the ISCA Workshop on Speech and Emotion, Belfast, Northern Ireland, pp 207\u2013212"},{"key":"1377_CR69","unstructured":"Polzin T, Waibel A (2000) Emotion-sensitive human-computer interfaces. In: the ISCA Workshop on Speech and Emotion, Belfast, Northern Ireland, pp 201\u2013206"},{"key":"1377_CR70","volume-title":"A dictionary of phonetics and phonology","author":"R Trask","year":"1996","unstructured":"Trask R (1996) A dictionary of phonetics and phonology. Burns & Oates, Routledge"},{"key":"1377_CR71","unstructured":"Klasmeyer G, Sendlmeier W (2000) Voice and emotional states. Voice Qual Meas: 339\u2013358"},{"key":"1377_CR72","doi-asserted-by":"crossref","unstructured":"Klasmeyer G (1997) The perceptual importance of selected voice quality parameters. In: IEEE international conference on acoustics, speech, and signal processing (ICASSP\u201997), Munich, Germany, pp 1615\u20131618","DOI":"10.1109\/ICASSP.1997.598808"},{"key":"1377_CR73","unstructured":"Klasmeyer G, Sendlmeier W (1995) Objective voice parameters to characterize the emotional content in speech. In: 13th international congress phonetic sciences (ICPhS\u201995), Stockholm, Sweden, pp 182\u2013185"},{"key":"1377_CR74","volume-title":"Digital processing of speech signals","author":"L Rabiner","year":"1978","unstructured":"Rabiner L, Schafer R (1978) Digital processing of speech signals. Prentice-hall, Englewood Cliffs"},{"issue":"3","key":"1377_CR75","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1037\/0096-1523.12.3.302","volume":"12","author":"F Tolkmitt","year":"1986","unstructured":"Tolkmitt F, Scherer K (1986) Effect of experimentally induced stress on vocal parameters. J Exp Psychol Hum Percept Perform 12(3):302\u2013313","journal-title":"J Exp Psychol Hum Percept Perform"},{"issue":"4B","key":"1377_CR76","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1121\/1.1913238","volume":"52","author":"C Williams","year":"1972","unstructured":"Williams C, Stevens K (1972) Emotions and speech: some acoustical correlates. J Acoust Soc Am 52(4B):1238\u20131250","journal-title":"J Acoust Soc Am"},{"key":"1377_CR77","first-page":"185","volume-title":"Handbook of emotions","author":"J Pittam","year":"1993","unstructured":"Pittam J, Scherer K (1993) Vocal expression and communication of emotion. In: Lewis M, Haviland JM (eds) Handbook of emotions. Guilford Press, New York, pp 185\u2013197"},{"key":"1377_CR78","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 KR (1996) Acoustic profiles in vocal emotion expression. J Pers Soc Psychol 70:614\u2013636","journal-title":"J Pers Soc Psychol"},{"key":"1377_CR79","unstructured":"Alter K, Rank E, Kotz S, Toepel U, Besson M, Schirmer A, Friederici A (2000) Accentuation and emotions-two different systems? In: ITRW on Speech and Emotion, Newcastle, Northern Ireland, pp 138\u2013142"},{"issue":"3","key":"1377_CR80","doi-asserted-by":"crossref","first-page":"1628","DOI":"10.1121\/1.421305","volume":"103","author":"D Michaelis","year":"1998","unstructured":"Michaelis D, Fr hlich M, Strube H (1998) Selection and combination of acoustic features for the description of pathologic voices. J Acoust Soc Am 103(3):1628\u20131639","journal-title":"J Acoust Soc Am"},{"key":"1377_CR81","doi-asserted-by":"crossref","unstructured":"Kasuya H, Endo Y, Saliu S (1993) Novel acoustic measurements of jitter and shimmer characteristics from pathological voice. In: EUROSPEECH \u201893, Berlin, Germany, pp 1973\u20131976","DOI":"10.21437\/Eurospeech.1993-446"},{"key":"1377_CR82","unstructured":"Chang C, Lin C (2001) LIBSVM: a library for support vector machines, 2001. Software available at http:\/\/www.csie.ntu.edu.tw\/cjlin\/libsvm"},{"key":"1377_CR83","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":"1377_CR84","unstructured":"Yu L, Liu H (2003) Feature selection for high-dimensional data: a fast correlation-based filter solution. In: The twentieth international conference on machine learning (ICML-2003), Washington DC, pp 856\u2013863"},{"key":"1377_CR85","doi-asserted-by":"crossref","unstructured":"Scherer S, Schwenker F, Palm G (2009) Classifier fusion for emotion recognition from speech. Adv Intell Environ: 95\u2013117","DOI":"10.1007\/978-0-387-76485-6_5"},{"key":"1377_CR86","doi-asserted-by":"crossref","unstructured":"Cichosz J, Slot K (2005) Low-dimensional feature space derivation for emotion recognition. In: INTERSPEECH-2005, Lisbon, Portugal, pp. 477\u2013480","DOI":"10.21437\/Interspeech.2005-320"},{"issue":"3","key":"1377_CR87","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"},{"issue":"2","key":"1377_CR88","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1109\/JSTSP.2009.2039171","volume":"4","author":"JF Gemmeke","year":"2010","unstructured":"Gemmeke JF, Van Hamme H, Cranen B, Boves L (2010) Compressive sensing for missing data imputation in noise robust speech recognition. IEEE J Select Top Sig Process 4(2):272\u2013287","journal-title":"IEEE J Select Top Sig Process"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-013-1377-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-013-1377-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-013-1377-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T02:21:25Z","timestamp":1715134885000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-013-1377-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,3,29]]},"references-count":88,"journal-issue":{"issue":"7-8","published-print":{"date-parts":[[2014,6]]}},"alternative-id":["1377"],"URL":"https:\/\/doi.org\/10.1007\/s00521-013-1377-z","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,3,29]]}}}