{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T15:20:19Z","timestamp":1776093619457,"version":"3.50.1"},"reference-count":84,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2019,10,26]],"date-time":"2019-10-26T00:00:00Z","timestamp":1572048000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,10,26]],"date-time":"2019-10-26T00:00:00Z","timestamp":1572048000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2020,1]]},"DOI":"10.1007\/s11042-019-08222-8","type":"journal-article","created":{"date-parts":[[2019,10,26]],"date-time":"2019-10-26T20:47:36Z","timestamp":1572122856000},"page":"1261-1289","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":68,"title":["Speech emotion recognition using discriminative dimension reduction by employing a modified quantum-behaved particle swarm optimization algorithm"],"prefix":"10.1007","volume":"79","author":[{"given":"Fatemeh","family":"Daneshfar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5103-7581","authenticated-orcid":false,"given":"Seyed Jahanshah","family":"Kabudian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,10,26]]},"reference":[{"issue":"17","key":"8222_CR1","doi-asserted-by":"crossref","first-page":"5145","DOI":"10.1007\/s00500-016-2110-5","volume":"21","author":"EM Albornoz","year":"2017","unstructured":"Albornoz EM, Milone DH, Rufiner HL (2017) Feature extraction based on bio-inspired model for robust emotion recognition. Soft Comput 21(17):5145\u20135158","journal-title":"Soft Comput"},{"issue":"5","key":"8222_CR2","doi-asserted-by":"crossref","first-page":"5571","DOI":"10.1007\/s11042-017-5292-7","volume":"78","author":"AM Badshah","year":"2019","unstructured":"Badshah AM, Rahim N, Ullah N, Ahmad J, Muhammad K, Lee MY, Kwon S, Baik SW (2019) Deep features-based speech emotion recognition for smart affective services. Multimed Tools Appl 78(5):5571\u20135589","journal-title":"Multimed Tools Appl"},{"issue":"3","key":"8222_CR3","first-page":"197","volume":"12","author":"M Bashirpour","year":"2016","unstructured":"Bashirpour M, Geravanchizadeh M (2016) Speech emotion recognition based on power normalized cepstral coefficients in noisy conditions. Iranian Journal of Electrical and Electronic Engineering 12(3):197\u2013205","journal-title":"Iranian Journal of Electrical and Electronic Engineering"},{"key":"8222_CR4","unstructured":"Bhargava M and Polzehl T (2012) Improving automatic emotion recognition from speech using rhythm and temporal feature, Proc. International Conference on Emerging Computation and Information Technologies"},{"key":"8222_CR5","doi-asserted-by":"crossref","unstructured":"Burkhardt F, Paeschke A, Rolfes M, Sendlmeier WF, and Weiss B (2005) A database of German emotional speech. Ninth European Conference on Speech Communication and Technology","DOI":"10.21437\/Interspeech.2005-446"},{"key":"8222_CR6","first-page":"38","volume-title":"Lecture Notes in Computer Science","author":"Cosimo A. Buscicchio","year":"2006","unstructured":"Buscicchio CA, G\u00f3recki P and Caponetti L (2006) Speech emotion recognition using spiking neural networks. International Symposium on Methodologies for Intelligent Systems. Springer Berlin Heidelberg"},{"issue":"4","key":"8222_CR7","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso C, Bulut M, Lee C-C, Kazemzadeh A, Mower E, Kim S, Chang JN, Lee S, Narayanan SS (2008) IEMOCAP: interactive emotional dyadic motion capture database. Lang Resour Eval 42(4):335","journal-title":"Lang Resour Eval"},{"issue":"6","key":"8222_CR8","doi-asserted-by":"crossref","first-page":"1154","DOI":"10.1016\/j.dsp.2012.05.007","volume":"22","author":"L Chen","year":"2012","unstructured":"Chen L, Mao X, Xue Y, Cheng LL (2012) Speech emotion recognition: features and classification models. Digital signal processing 22(6):1154\u20131160","journal-title":"Digital signal processing"},{"key":"8222_CR9","unstructured":"Cho Y-H, Park K-S, and Pak RJ (2007) Speech emotion pattern recognition agent in mobile communication environment using fuzzy-SVM. Fuzzy information and engineering. Springer Berlin Heidelberg, 419\u2013430"},{"key":"8222_CR10","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.bica.2018.01.002","volume":"23","author":"RV Darekar","year":"2018","unstructured":"Darekar RV, Dhande AP (2018) Emotion recognition from Marathi speech database using adaptive artificial neural network. Biologically Inspired Cognitive Architectures 23:35\u201342","journal-title":"Biologically Inspired Cognitive Architectures"},{"key":"8222_CR11","doi-asserted-by":"crossref","unstructured":"Deb S, and Dandapat S (2016) Emotion classification using residual sinusoidal peak amplitude. 2016 International Conference on Signal Processing and Communications (SPCOM). IEEE","DOI":"10.1109\/SPCOM.2016.7746697"},{"key":"8222_CR12","doi-asserted-by":"crossref","unstructured":"Deb S, and Dandapat S (2017) Exploration of phase information for speech emotion classification. 2017 Twenty-third National Conference on Communications (NCC). IEEE","DOI":"10.1109\/NCC.2017.8077114"},{"key":"8222_CR13","doi-asserted-by":"crossref","unstructured":"Degottex G, Kane J, Drugman T, Raitio T, and Scherer S (2014) COVAREP\u2014A collaborative voice analysis repository for speech technologies. 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE","DOI":"10.1109\/ICASSP.2014.6853739"},{"issue":"9","key":"8222_CR14","doi-asserted-by":"crossref","first-page":"1068","DOI":"10.1109\/LSP.2014.2324759","volume":"21","author":"J Deng","year":"2014","unstructured":"Deng J, Zhang Z, Eyben F, Schuller B (2014) Autoencoder-based unsupervised domain adaptation for speech emotion recognition. IEEE Signal Processing Letters 21(9):1068\u20131072","journal-title":"IEEE Signal Processing Letters"},{"key":"8222_CR15","unstructured":"Duda RO, Hart PE, and Stork DG. (2001) Pattern classification, 2ndEd. John Wiley & Sons"},{"issue":"6","key":"8222_CR16","doi-asserted-by":"crossref","first-page":"1056","DOI":"10.1109\/TASLP.2014.2319157","volume":"22","author":"MJ Gangeh","year":"2014","unstructured":"Gangeh MJ, Fewzee P, Ghodsi A, Kamel MS, Karray F (2014) Multiview supervised dictionary learning in speech emotion recognition. IEEE\/ACM Transactions on Audio, Speech, and Language Processing 22(6):1056\u20131068","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"8","key":"8222_CR17","doi-asserted-by":"crossref","first-page":"2115","DOI":"10.1007\/s00521-011-0643-1","volume":"21","author":"D Gharavian","year":"2012","unstructured":"Gharavian D, Sheikhan M, Nazerieh A, Garoucy S (2012) Speech emotion recognition using FCBF feature selection method and GA-optimized fuzzy ARTMAP neural network. Neural Comput & Applic 21(8):2115\u20132126","journal-title":"Neural Comput & Applic"},{"issue":"2","key":"8222_CR18","doi-asserted-by":"crossref","first-page":"2331","DOI":"10.1007\/s11042-015-3180-6","volume":"76","author":"D Gharavian","year":"2017","unstructured":"Gharavian D, Bejani M, Sheikhan M (2017) Audio-visual emotion recognition using FCBF feature selection method and particle swarm optimization for fuzzy ARTMAP neural networks. Multimed Tools Appl 76(2):2331\u20132352","journal-title":"Multimed Tools Appl"},{"key":"8222_CR19","doi-asserted-by":"crossref","unstructured":"Ghosh S, Laksana E, Morency L-P, and Scherer S (2016) Representation Learning for Speech Emotion Recognition. Interspeech","DOI":"10.21437\/Interspeech.2016-692"},{"issue":"10","key":"8222_CR20","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1016\/j.specom.2007.01.010","volume":"49","author":"M Grimm","year":"2007","unstructured":"Grimm M, Kroschel K, Mower E, Narayanan S (2007) Primitives-based evaluation and estimation of emotions in speech. Speech Comm 49(10):787\u2013800","journal-title":"Speech Comm"},{"key":"8222_CR21","doi-asserted-by":"crossref","unstructured":"Haq S, and Jackson PJB. (2011) Multimodal emotion recognition. Machine audition: principles, algorithms and systems. IGI Global, 398\u2013423","DOI":"10.4018\/978-1-61520-919-4.ch017"},{"key":"8222_CR22","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.eswa.2016.10.035","volume":"69","author":"CK Yogesh","year":"2017","unstructured":"Yogesh CK, Hariharan M, Ngadiran R, Adom AH, Yaacob S, Berkai C, Polat K (2017) A new hybrid PSO assisted biogeography-based optimization for emotion and stress recognition from speech signal. Expert Syst Appl 69:149\u2013158","journal-title":"Expert Syst Appl"},{"issue":"4","key":"8222_CR23","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H Hermansky","year":"1990","unstructured":"Hermansky H (1990) Perceptual linear predictive (PLP) analysis of speech. The Journal of the Acoustical Society of America 87(4):1738\u20131752","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"4","key":"8222_CR24","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1049\/iet-spr.2013.0446","volume":"9","author":"Y Huang","year":"2015","unstructured":"Huang Y, Wu A, Zhang G, Li Y (2015) Extraction of adaptive wavelet packet filter-bank-based acoustic feature for speech emotion recognition. IET Signal Processing 9(4):341\u2013348","journal-title":"IET Signal Processing"},{"issue":"5","key":"8222_CR25","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1631\/FITEE.1400323","volume":"16","author":"Z-w Huang","year":"2015","unstructured":"Huang Z-w, Xue W-t, Mao Q-r (2015) Speech emotion recognition with unsupervised feature learning. Frontiers of Information Technology & Electronic Engineering 16(5):358\u2013366","journal-title":"Frontiers of Information Technology & Electronic Engineering"},{"issue":"5","key":"8222_CR26","doi-asserted-by":"crossref","first-page":"6785","DOI":"10.1007\/s11042-016-3354-x","volume":"76","author":"Z Huang","year":"2017","unstructured":"Huang Z, Xue W, Mao Q, Zhan Y (2017) Unsupervised domain adaptation for speech emotion recognition using PCANet. Multimed Tools Appl 76(5):6785\u20136799","journal-title":"Multimed Tools Appl"},{"key":"8222_CR27","doi-asserted-by":"crossref","unstructured":"Idris I and Salam MS (2016) Improved Speech Emotion Classification from Spectral Coefficient Optimization. Advances in Machine Learning and Signal Processing. Springer International Publishing, 247\u2013257","DOI":"10.1007\/978-3-319-32213-1_22"},{"key":"8222_CR28","unstructured":"Junqua J-C, and Haton J-P (2012) Robustness in automatic speech recognition: Fundamentals and applications. Vol. 341. Springer Science & Business Media"},{"key":"8222_CR29","doi-asserted-by":"crossref","unstructured":"Kabudian J, Mehdi Homayounpour M, and Mohammad Ahadi S (2008) Time-inhomogeneous hidden Bernoulli model: An alternative to hidden Markov model for automatic speech recognition. 2008 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE","DOI":"10.1109\/ICASSP.2008.4518556"},{"key":"8222_CR30","doi-asserted-by":"crossref","unstructured":"Kadiri SR, Gangamohan P, Gangashetty SV, and Yegnanarayana B (2015) Analysis of excitation source features of speech for emotion recognition. In Sixteenth Annual Conference of the International Speech Communication Association","DOI":"10.21437\/Interspeech.2015-329"},{"key":"8222_CR31","doi-asserted-by":"crossref","unstructured":"Kalinli O (2016) Analysis of Multi-Lingual Emotion Recognition Using Auditory Attention Features. INTERSPEECH","DOI":"10.21437\/Interspeech.2016-1557"},{"key":"8222_CR32","unstructured":"Keyvanrad MA, and Homayounpour MM. (2014) A brief survey on deep belief networks and introducing a new object oriented toolbox (DeeBNet). arXiv preprint arXiv:1408.3264"},{"key":"8222_CR33","doi-asserted-by":"crossref","unstructured":"Khan A and Roy UK (2017) Emotion recognition using prosodie and spectral features of speech and Na\u00efve Bayes Classifier. 2017 international conference on wireless communications, signal processing and networking (WiSPNET). IEEE","DOI":"10.1109\/WiSPNET.2017.8299916"},{"issue":"3","key":"8222_CR34","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1109\/TMECH.2008.2008644","volume":"14","author":"EH Kim","year":"2009","unstructured":"Kim EH, Hyun KH, Kim SH, Kwak YK (2009) Improved emotion recognition with a novel speaker-independent feature. IEEE\/ASME Transactions on Mechatronics 14(3):317\u2013325","journal-title":"IEEE\/ASME Transactions on Mechatronics"},{"key":"8222_CR35","first-page":"180","volume-title":"Lecture Notes in Computer Science","author":"Xiang Li","year":"2010","unstructured":"Li X, Li X, Zheng X, Zhang D (2010) EMD-TEO Based speech emotion recognition. Life System Modeling and Intelligent Computing. Springer Berlin Heidelberg. 180\u2013189"},{"key":"8222_CR36","doi-asserted-by":"crossref","unstructured":"Li Y, Chao L, Liu Y, Bao W, and Tao J (2015) From simulated speech to natural speech, what are the robust features for emotion recognition?. 2015 International Conference on Affective Computing and Intelligent Interaction (ACII). IEEE","DOI":"10.1109\/ACII.2015.7344597"},{"key":"8222_CR37","doi-asserted-by":"crossref","unstructured":"Li P, Song Y, McLoughlin I, Guo W, and Dai L (2018) An Attention Pooling based Representation Learning Method for Speech Emotion Recognition. Proc. Interspeech (2018): 3087\u20133091","DOI":"10.21437\/Interspeech.2018-1242"},{"key":"8222_CR38","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.neucom.2018.05.005","volume":"309","author":"Z-T Liu","year":"2018","unstructured":"Liu Z-T, Xie Q, Wu M, Cao W-H, Mei Y, Mao J-W (2018) Speech emotion recognition based on an improved brain emotion learning model. Neurocomputing 309:145\u2013156","journal-title":"Neurocomputing"},{"key":"8222_CR39","doi-asserted-by":"crossref","unstructured":"Lotfidereshgi R, and Gournay P (2017) Biologically inspired speech emotion recognition. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE","DOI":"10.1109\/ICASSP.2017.7953135"},{"issue":"6","key":"8222_CR40","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, Hern\u00e1ez I (2010) Feature analysis and evaluation for automatic emotion identification in speech. IEEE Transactions on Multimedia 12(6):490\u2013501","journal-title":"IEEE Transactions on Multimedia"},{"key":"8222_CR41","unstructured":"Mak MW (2016) Feature Selection and Nuisance Attribute Projection for Speech Emotion Recognition, Technical Report and Lecture Note Series, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University"},{"issue":"8","key":"8222_CR42","doi-asserted-by":"crossref","first-page":"2203","DOI":"10.1109\/TMM.2014.2360798","volume":"16","author":"Q Mao","year":"2014","unstructured":"Mao Q, Dong M, Huang Z, Zhan Y (2014) Learning salient features for speech emotion recognition using convolutional neural networks. IEEE Transactions on Multimedia 16(8):2203\u20132213","journal-title":"IEEE Transactions on Multimedia"},{"key":"8222_CR43","doi-asserted-by":"crossref","unstructured":"Mirhosseini SH, Yarmohamadi H, and Kabudian J (2014) MiGSA: A new simulated annealing algorithm with mixture distribution as generating function. 2014 4th International Conference on Computer and Knowledge Engineering (ICCKE). IEEE","DOI":"10.1109\/ICCKE.2014.6993413"},{"issue":"6","key":"8222_CR44","doi-asserted-by":"crossref","first-page":"1496","DOI":"10.1109\/TCYB.2016.2549639","volume":"47","author":"K Mistry","year":"2016","unstructured":"Mistry K, Zhang L, Neoh SC, Lim CP, Fielding B (2016) A micro-GA embedded PSO feature selection approach to intelligent facial emotion recognition. IEEE Transactions on Cybernetics 47(6):1496\u20131509","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"1","key":"8222_CR45","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/TBME.2007.900562","volume":"55","author":"E Moore II","year":"2007","unstructured":"Moore E II, Clements MA, Peifer JW, Weisser L (2007) Critical analysis of the impact of glottal features in the classification of clinical depression in speech. IEEE Trans Biomed Eng 55(1):96\u2013107","journal-title":"IEEE Trans Biomed Eng"},{"issue":"3","key":"8222_CR46","doi-asserted-by":"crossref","first-page":"e0120344","DOI":"10.1371\/journal.pone.0120344","volume":"10","author":"H Muthusamy","year":"2015","unstructured":"Muthusamy H, Polat K, Yaacob S (2015) Particle swarm optimization based feature enhancement and feature selection for improved emotion recognition in speech and glottal signals. PLoS One 10(3):e0120344","journal-title":"PLoS One"},{"key":"8222_CR47","doi-asserted-by":"crossref","unstructured":"Neekabadi A, and Kabudian SJ. (2018) A New Quantum-PSO Metaheuristic and Its Application to ARMA Modeling of Speech Spectrum. 2018 4th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS). IEEE","DOI":"10.1109\/ICSPIS.2018.8700530"},{"issue":"2","key":"8222_CR48","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1007\/s10772-017-9396-2","volume":"20","author":"F Noroozi","year":"2017","unstructured":"Noroozi F, Sapi\u0144ski T, Kami\u0144ska D, Anbarjafari G (2017) Vocal-based emotion recognition using random forests and decision tree. International Journal of Speech Technology 20(2):239\u2013246","journal-title":"International Journal of Speech Technology"},{"key":"8222_CR49","doi-asserted-by":"crossref","unstructured":"Pant M, Thangaraj R, and Abraham A (2008) A new quantum behaved particle swarm optimization. Proceedings of the 10th annual conference on Genetic and evolutionary computation. ACM","DOI":"10.1145\/1389095.1389108"},{"issue":"2","key":"8222_CR50","doi-asserted-by":"crossref","first-page":"26","DOI":"10.3390\/computation5020026","volume":"5","author":"M Papakostas","year":"2017","unstructured":"Papakostas M, Spyrou E, Giannakopoulos T, Siantikos G, Sgouropoulos D, Mylonas P, Makedon F (2017) Deep visual attributes vs. hand-crafted audio features on multidomain speech emotion recognition. Computation 5(2):26","journal-title":"Computation"},{"issue":"3","key":"8222_CR51","doi-asserted-by":"crossref","first-page":"1590","DOI":"10.1109\/TCE.2009.5278031","volume":"55","author":"J-S Park","year":"2009","unstructured":"Park J-S, Kim J-H, Yung-Hwan O (2009) Feature vector classification based speech emotion recognition for service robots. IEEE Trans Consum Electron 55(3):1590\u20131596","journal-title":"IEEE Trans Consum Electron"},{"key":"8222_CR52","doi-asserted-by":"crossref","unstructured":"Pohjalainen J and Alku P (2014) Multi-scale modulation filtering in automatic detection of emotions in telephone speech. Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on. IEEE","DOI":"10.1109\/ICASSP.2014.6853743"},{"key":"8222_CR53","doi-asserted-by":"crossref","unstructured":"Satt A, Rozenberg S, and Hoory R (2017) Efficient Emotion Recognition from Speech Using Deep Learning on Spectrograms. INTERSPEECH","DOI":"10.21437\/Interspeech.2017-200"},{"issue":"1","key":"8222_CR54","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/s00521-012-0814-8","volume":"23","author":"M Sheikhan","year":"2013","unstructured":"Sheikhan M, Bejani M, Gharavian D (2013) Modular neural-SVM scheme for speech emotion recognition using ANOVA feature selection method. Neural Comput & Applic 23(1):215\u2013227","journal-title":"Neural Comput & Applic"},{"key":"8222_CR55","doi-asserted-by":"crossref","unstructured":"Shekofteh Y, Kabudian J, Goodarzi MM, Rezaei IS (2012) Confidence measure improvement using useful predictor features and support vector machines. 20th Iranian Conference on Electrical Engineering (ICEE2012). IEEE","DOI":"10.1109\/IranianCEE.2012.6292531"},{"key":"8222_CR56","doi-asserted-by":"crossref","unstructured":"Shirani A, and Nilchi ARN (2016) Speech Emotion Recognition based on SVM as Both Feature Selector and Classifier. International Journal of Image, Graphics & Signal Processing 8, 4","DOI":"10.5815\/ijigsp.2016.04.05"},{"issue":"4","key":"8222_CR57","doi-asserted-by":"crossref","first-page":"518","DOI":"10.17516\/1997-1397-2016-9-4-518-523","volume":"9","author":"M Sidorov","year":"2016","unstructured":"Sidorov M, Minker W, Semenkin ES (2016) Speech-based emotion recognition and static speaker representation. Journal of the Siberian Federal University The series Mathematics and Physics 9(4):518\u2013523","journal-title":"Journal of the Siberian Federal University The series Mathematics and Physics"},{"key":"8222_CR58","doi-asserted-by":"crossref","unstructured":"Sinith MS, Aswathi E, Deepa TM, Shameema CP and Rajan S (2015) Emotion recognition from audio signals using Support Vector Machine. 2015 IEEE Recent Advances in Intelligent Computational Systems (RAICS). IEEE","DOI":"10.1109\/RAICS.2015.7488403"},{"issue":"1","key":"8222_CR59","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1049\/el.2014.3339","volume":"51","author":"P Song","year":"2015","unstructured":"Song P, Jin Y, Cheng Z, Zhao L (2015) Speech emotion recognition method based on hidden factor analysis. Electron Lett 51(1):112\u2013114","journal-title":"Electron Lett"},{"key":"8222_CR60","doi-asserted-by":"crossref","unstructured":"Stewart GW (1998) Matrix Algorithms: Volume 1: Basic Decompositions. Vol. 1. SIAM","DOI":"10.1137\/1.9781611971408"},{"key":"8222_CR61","doi-asserted-by":"crossref","unstructured":"Stuhlsatz A, Meyer C, Eyben F, Zielke T, Meier G, and Schuller B. (2011) Deep neural networks for acoustic emotion recognition: raising the benchmarks. In 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5688\u20135691. IEEE","DOI":"10.1109\/ICASSP.2011.5947651"},{"issue":"3","key":"8222_CR62","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1007\/s10772-015-9272-x","volume":"18","author":"Y Sun","year":"2015","unstructured":"Sun Y, Wen G (2015) Emotion recognition using semi-supervised feature selection with speaker normalization. International Journal of Speech Technology 18(3):317\u2013331","journal-title":"International Journal of Speech Technology"},{"issue":"6","key":"8222_CR63","doi-asserted-by":"crossref","first-page":"8305","DOI":"10.1007\/s11042-016-3487-y","volume":"76","author":"Y Sun","year":"2017","unstructured":"Sun Y, Wen G (2017) Ensemble softmax regression model for speech emotion recognition. Multimed Tools Appl 76(6):8305\u20138328","journal-title":"Multimed Tools Appl"},{"key":"8222_CR64","unstructured":"Sun J, Lai C-H, and Wu X-J. (2011) Particle swarm optimisation: classical and quantum perspectives. CRC Press"},{"key":"8222_CR65","doi-asserted-by":"crossref","unstructured":"Tzinis E, and Potamianos A (2017) Segment-based speech emotion recognition using recurrent neural networks. 2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII). IEEE","DOI":"10.1109\/ACII.2017.8273599"},{"key":"8222_CR66","doi-asserted-by":"crossref","unstructured":"Tzinis E, Paraskevopoulos G, Baziotis C, and Potamianos A. (2018) Integrating Recurrence Dynamics for Speech Emotion Recognition. Proc. Interspeech (2018): 927\u2013931","DOI":"10.21437\/Interspeech.2018-1377"},{"key":"8222_CR67","unstructured":"Vasquez-Correa JC, Arias-Vergara T, Orozco-Arroyave JR, Vargas-Bonilla JF and Noeth E (2016) Wavelet-based time-frequency representations for automatic recognition of emotions from speech. Speech Communication; 12. ITG Symposium. VDE"},{"issue":"9","key":"8222_CR68","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 Comm 48(9):1162\u20131181","journal-title":"Speech Comm"},{"issue":"1","key":"8222_CR69","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1109\/TAFFC.2015.2392101","volume":"6","author":"K Wang","year":"2015","unstructured":"Wang K, An N, Li BN, Zhang Y, Li L (2015) Speech emotion recognition using Fourier parameters. IEEE Trans Affect Comput 6(1):69\u201375","journal-title":"IEEE Trans Affect Comput"},{"key":"8222_CR70","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1016\/j.neucom.2017.08.015","volume":"272","author":"S-H Wang","year":"2018","unstructured":"Wang S-H, Phillips P, Dong Z-C, Zhang Y-D (2018) Intelligent facial emotion recognition based on stationary wavelet entropy and Jaya algorithm. Neurocomputing 272:668\u2013676","journal-title":"Neurocomputing"},{"key":"8222_CR71","doi-asserted-by":"crossref","unstructured":"Wen G, Li H, Huang J, Li D, and Xun E (2017) Random deep belief networks for recognizing emotions from speech signals. Computational intelligence and neuroscience 2017","DOI":"10.1155\/2017\/1945630"},{"issue":"2","key":"8222_CR72","first-page":"751","volume":"205","author":"M Xi","year":"2008","unstructured":"Xi M, Sun J, Xu W (2008) An improved quantum-behaved particle swarm optimization algorithm with weighted mean best position. Appl Math Comput 205(2):751\u2013759","journal-title":"Appl Math Comput"},{"key":"8222_CR73","doi-asserted-by":"crossref","unstructured":"Xu X, Deng J, Zheng W, Zhao L, and Schuller B (2015) Dimensionality reduction for speech emotion features by multiscale kernels. Sixteenth Annual Conference of the International Speech Communication Association","DOI":"10.21437\/Interspeech.2015-335"},{"issue":"1","key":"8222_CR74","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/s10772-016-9364-2","volume":"20","author":"N Yang","year":"2017","unstructured":"Yang N, Yuan J, Zhou Y, Demirkol I, Duan Z, Heinzelman W, Sturge-Apple M (2017) Enhanced multiclass SVM with thresholding fusion for speech-based emotion classification. International Journal of Speech Technology 20(1):27\u201341","journal-title":"International Journal of Speech Technology"},{"issue":"2","key":"8222_CR75","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1016\/j.specom.2007.07.006","volume":"50","author":"UH Yapanel","year":"2008","unstructured":"Yapanel UH, Hansen JHL (2008) A new perceptually motivated MVDR-based acoustic front-end (PMVDR) for robust automatic speech recognition. Speech Comm 50(2):142\u2013152","journal-title":"Speech Comm"},{"key":"8222_CR76","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.asoc.2017.03.013","volume":"56","author":"CK Yogesh","year":"2017","unstructured":"Yogesh CK, Hariharan M, Ngadiran R, Adom AH, Yaacob S, Polat K (2017) Hybrid BBO_PSO and higher order spectral features for emotion and stress recognition from natural speech. Appl Soft Comput 56:217\u2013232","journal-title":"Appl Soft Comput"},{"key":"8222_CR77","doi-asserted-by":"crossref","unstructured":"Y\u00fcnc\u00fc E, Hacihabiboglu H, and Bozsahin C (2014) Automatic speech emotion recognition using auditory models with binary decision tree and svm. 2014 22nd International Conference on Pattern Recognition. IEEE","DOI":"10.1109\/ICPR.2014.143"},{"key":"8222_CR78","unstructured":"Zaidan NA, and Salam MS (2016) MFCC Global Features Selection in Improving Speech Emotion Recognition Rate. Advances in Machine Learning and Signal Processing. Springer International Publishing, 141\u2013153"},{"issue":"5","key":"8222_CR79","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1109\/LSP.2014.2311435","volume":"21","author":"L Zao","year":"2014","unstructured":"Zao L, Cavalcante D, Coelho R (2014) Time-frequency feature and AMS-GMM mask for acoustic emotion classification. IEEE Signal Processing Letters 21(5):620\u2013624","journal-title":"IEEE Signal Processing Letters"},{"key":"8222_CR80","doi-asserted-by":"crossref","unstructured":"Zhang S, Zhao X, and Lei B (2013) Speech emotion recognition using an enhanced kernel isomap for human-robot interaction, Int J Adv Robot Syst, 10","DOI":"10.5772\/55403"},{"issue":"6","key":"8222_CR81","doi-asserted-by":"crossref","first-page":"1576","DOI":"10.1109\/TMM.2017.2766843","volume":"20","author":"S Zhang","year":"2017","unstructured":"Zhang S, Zhang S, Huang T, Gao W (2017) Speech emotion recognition using deep convolutional neural network and discriminant temporal pyramid matching. IEEE Transactions on Multimedia 20(6):1576\u20131590","journal-title":"IEEE Transactions on Multimedia"},{"key":"8222_CR82","doi-asserted-by":"crossref","unstructured":"Zhao Z, Zhao Y, Bao Z, Wang H, Zhang Z, and Li C (2018) Deep Spectrum Feature Representations for Speech Emotion Recognition. Proceedings of the Joint Workshop of the 4th Workshop on Affective Social Multimedia Computing and first Multi-Modal Affective Computing of Large-Scale Multimedia Data. ACM","DOI":"10.1145\/3267935.3267948"},{"issue":"5","key":"8222_CR83","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1109\/LSP.2014.2308954","volume":"21","author":"W Zheng","year":"2014","unstructured":"Zheng W, Xin M, Wang X, Wang B (2014) A novel speech emotion recognition method via incomplete sparse least square regression. IEEE Signal Processing Letters 21(5):569\u2013572","journal-title":"IEEE Signal Processing Letters"},{"issue":"5","key":"8222_CR84","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1109\/LSP.2016.2537926","volume":"23","author":"Y Zong","year":"2016","unstructured":"Zong Y, Zheng W, Zhang T, Huang X (2016) Cross-corpus speech emotion recognition based on domain-adaptive least-squares regression. IEEE Signal Processing Letters 23(5):585\u2013589","journal-title":"IEEE Signal Processing Letters"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08222-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-08222-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08222-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,2]],"date-time":"2022-10-02T19:24:43Z","timestamp":1664738683000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-08222-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,26]]},"references-count":84,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2020,1]]}},"alternative-id":["8222"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-08222-8","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,26]]},"assertion":[{"value":"18 April 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 September 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 October 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}