{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:28:32Z","timestamp":1740122912755,"version":"3.37.3"},"reference-count":83,"publisher":"Springer Science and Business Media LLC","issue":"47-48","license":[{"start":{"date-parts":[[2020,9,18]],"date-time":"2020-09-18T00:00:00Z","timestamp":1600387200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,9,18]],"date-time":"2020-09-18T00:00:00Z","timestamp":1600387200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1007\/s11042-020-09591-1","type":"journal-article","created":{"date-parts":[[2020,9,18]],"date-time":"2020-09-18T03:50:56Z","timestamp":1600401056000},"page":"35739-35759","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Recognition of emotion from speech using evolutionary cepstral coefficients"],"prefix":"10.1007","volume":"79","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5408-0777","authenticated-orcid":false,"given":"Ali","family":"Bakhshi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephan","family":"Chalup","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Harimi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seyed Mostafa","family":"Mirhassani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,18]]},"reference":[{"issue":"2","key":"9591_CR1","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/s10772-012-9133-9","volume":"15","author":"RK Aggarwal","year":"2012","unstructured":"Aggarwal RK, Dave M (2012) Filterbank optimization for robust asr using ga and pso. Int J Speech Technol 15(2):191\u2013201","journal-title":"Int J Speech Technol"},{"issue":"3\u20134","key":"9591_CR2","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/0167-6393(82)90015-2","volume":"1","author":"TV Ananthapadmanabha","year":"1982","unstructured":"Ananthapadmanabha TV, Fant G (1982) Calculation of true glottal flow and its components. Speech Comm 1(3\u20134):167\u2013184","journal-title":"Speech Comm"},{"key":"9591_CR3","doi-asserted-by":"crossref","unstructured":"Anne KR, Kuchibhotla S, Vankayalapati HD (2015) Acoustic modeling for emotion recognition Springer","DOI":"10.1007\/978-3-319-15530-2"},{"key":"9591_CR4","doi-asserted-by":"crossref","unstructured":"Arroabarren I, Carlosena A (2006) Voice production mechanisms of vocal vibrato in male singers. In: IEEE Transactions on Audio Speech, and Language Processing, vol 15, pp 320\u2013332","DOI":"10.1109\/TASL.2006.872607"},{"key":"9591_CR5","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780195099713.001.0001","volume-title":"Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms","author":"T Back","year":"1996","unstructured":"Back T (1996) Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms. Oxford University Press, New York"},{"issue":"5","key":"9591_CR6","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, Mi YL, 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"},{"key":"9591_CR7","doi-asserted-by":"crossref","unstructured":"Bao W, Li Y, Gu M, Yang M, Li H, Chao L, Tao J (2014) Building a chinese natural emotional audio-visual database. In: 2014 12th International Conference on Signal Processing (ICSP). IEEE, pp 583\u2013587","DOI":"10.1109\/ICOSP.2014.7015071"},{"key":"9591_CR8","unstructured":"Batliner A, Steidl S, N\u00f6th E (2008) Releasing a thoroughly annotated and processed spontaneous emotional database: the fau aibo emotion corpus. In: Proc. of a Satellite Workshop of LREC, vol 28"},{"key":"9591_CR9","unstructured":"Bhargava M, Polzehl T (2013) Improving automatic emotion recognition from speech using rhythm and temporal feature. arXiv:1303.1761"},{"issue":"7-8","key":"9591_CR10","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 communication 52(7-8):613\u2013625","journal-title":"Speech communication"},{"key":"9591_CR11","doi-asserted-by":"crossref","unstructured":"Burkhardt F, Paeschke A, Rolfes M, Sendlmeier WF, Benjamin W (2005) A database of german emotional speech","DOI":"10.21437\/Interspeech.2005-446"},{"issue":"4","key":"9591_CR12","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, Iemocap SSN (2008) Interactive emotional dyadic motion capture database. Lang Resour Eval 42(4):335","journal-title":"Lang Resour Eval"},{"key":"9591_CR13","doi-asserted-by":"crossref","unstructured":"Charbuillet C, Gas B, Chetouani M, Zarader JL (2007) Multi filter bank approach for speaker verification based on genetic algorithm. In: International Conference on Nonlinear Speech Processing, pages 105\u2013113. Springer","DOI":"10.1007\/978-3-540-77347-4_7"},{"issue":"9","key":"9591_CR14","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1016\/j.specom.2009.01.005","volume":"51","author":"C Charbuillet","year":"2009","unstructured":"Charbuillet C, Gas B, Chetouani M, strategy J-LZ (2009) Optimizing feature complementarity by evolution Application to automatic speaker verification. Speech Comm 51(9):724\u2013731","journal-title":"Speech Comm"},{"issue":"1","key":"9591_CR15","doi-asserted-by":"crossref","first-page":"1261","DOI":"10.1007\/s11042-019-08222-8","volume":"79","author":"F Daneshfar","year":"2020","unstructured":"Daneshfar F, Kabudian SJ (2020) Speech emotion recognition using discriminative dimension reduction by employing a modified quantum-behaved particle swarm optimization algorithm. Multimedia Tools and Applications 79 (1):1261\u20131289","journal-title":"Multimedia Tools and Applications"},{"issue":"4","key":"9591_CR16","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S Davis","year":"1980","unstructured":"Davis S, Mermelstein P (1980) Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics Speech, and Signal Processing 28(4):357\u2013366","journal-title":"IEEE Transactions on Acoustics Speech, and Signal Processing"},{"key":"9591_CR17","doi-asserted-by":"crossref","unstructured":"Davis SB, Mermelstein P (1990) Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. In: Readings in speech recognition, pages 65\u201374. Elsevier","DOI":"10.1016\/B978-0-08-051584-7.50010-3"},{"key":"9591_CR18","doi-asserted-by":"crossref","unstructured":"Deb S, Dandapat S (2016) Emotion classification using residual sinusoidal peak amplitude. In: International Conference on Signal Processing and Communications (SPCOM) pages 1\u20135 IEEE","DOI":"10.1109\/SPCOM.2016.7746697"},{"key":"9591_CR19","doi-asserted-by":"crossref","unstructured":"Deb Suman, Dandapat S (2017) Exploration of phase information for speech emotion classification. In: Twenty-third National Conference on Communications (NCC), pages 1\u20135 IEEE, p 2017","DOI":"10.1109\/NCC.2017.8077114"},{"key":"9591_CR20","doi-asserted-by":"crossref","unstructured":"Deller John R, Proakis John G, Hansen John HL (2000) Discrete-time processing of speech signals Institute of Electrical and Electronics Engineers","DOI":"10.1109\/9780470544402"},{"issue":"8","key":"9591_CR21","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/s00521-016-2712-y","volume":"29","author":"S Demircan","year":"2018","unstructured":"Demircan S, Kahramanli H (2018) Application of fuzzy c-means clustering algorithm to spectral features for emotion classification from speech. Neural Comput & Applic 29(8):59\u201366","journal-title":"Neural Comput & Applic"},{"key":"9591_CR22","doi-asserted-by":"crossref","unstructured":"Demuynck K, Duchateau J, Compernolle DV, Wambacq P (1998) Improved feature decorrelation for hmm-based speech recognition. In: Fifth International Conference on Spoken Language Processing","DOI":"10.21437\/ICSLP.1998-172"},{"issue":"3","key":"9591_CR23","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1016\/j.jestch.2018.04.005","volume":"21","author":"M Dua","year":"2018","unstructured":"Dua M, Aggarwal RK, Biswas M (2018) Performance evaluation of hindi speech recognition system using optimized filterbanks. Engineering Science and Technology, an International Journal 21(3):389\u2013398","journal-title":"Engineering Science and Technology, an International Journal"},{"issue":"3","key":"9591_CR24","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M El Ayadi","year":"2011","unstructured":"El Ayadi M, Kamel MS, Fakhri K (2011) Survey on speech emotion recognition Features, classification schemes, and databases. Pattern Recogn 44(3):572\u2013587","journal-title":"Pattern Recogn"},{"key":"9591_CR25","doi-asserted-by":"crossref","unstructured":"Graves A, Jaitly N (2014) Towards end-to-end speech recognition with recurrent neural networks","DOI":"10.1109\/ICASSP.2013.6638947"},{"issue":"10-11","key":"9591_CR26","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 (10-11):787\u2013800","journal-title":"Speech Comm"},{"key":"9591_CR27","doi-asserted-by":"crossref","unstructured":"Holland JH, et al. (1992) Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence MIT Press","DOI":"10.7551\/mitpress\/1090.001.0001"},{"issue":"5","key":"9591_CR28","doi-asserted-by":"crossref","first-page":"1595","DOI":"10.1007\/s11771-011-0877-1","volume":"18","author":"L-X Huang","year":"2011","unstructured":"Huang L-X, Evangelista G, Zhang X-Y (2011) Adaptive bands filter bank optimized by genetic algorithm for robust speech recognition system. Journal of Central South University of Technology 18(5):1595","journal-title":"Journal of Central South University of Technology"},{"key":"9591_CR29","volume-title":"Spoken language processing: a guide to theory, algorithm and system development, vol 1","author":"X Huang","year":"2001","unstructured":"Huang X, Acero A, Hon H-W, Reddy R (2001) Spoken language processing: a guide to theory, algorithm and system development, vol 1. Prentice Hall PTR, Upper Saddle River, NJ, USA"},{"key":"9591_CR30","first-page":"59","volume":"101894","author":"D Issa","year":"2020","unstructured":"Issa D, Fatih Demirci M, Yazici A (2020) Speech emotion recognition with deep convolutional neural networks. Biomedical Signal Processing and Control 101894:59","journal-title":"Biomedical Signal Processing and Control"},{"key":"9591_CR31","volume-title":"Surrey audio-visual expressed emotion (savee) database University of Surrey","author":"P Jackson","year":"2014","unstructured":"Jackson P, Haq S (2014) Surrey audio-visual expressed emotion (savee) database University of Surrey. Guildford, UK"},{"issue":"4","key":"9591_CR32","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1109\/89.397093","volume":"3","author":"CR Jankowski","year":"1995","unstructured":"Jankowski CR, Vo H-DH, Lippmann RP (1995) A comparison of signal processing front ends for automatic word recognition. IEEE Transactions on Speech and Audio processing 3(4):286\u2013293","journal-title":"IEEE Transactions on Speech and Audio processing"},{"issue":"3","key":"9591_CR33","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1080\/00401706.1991.10484833","volume":"33","author":"BH Juang","year":"1991","unstructured":"Juang BH, Rabiner LR (1991) Hidden markov models for speech recognition. Technometrics 33(3):251\u2013272","journal-title":"Technometrics"},{"key":"9591_CR34","doi-asserted-by":"crossref","unstructured":"Kalinli O (2016) Analysis of multi-lingual emotion recognition using auditory attention features. In: INTERSPEECH 8-12 Sep 2016 San Francisco 3613\u20133617 09","DOI":"10.21437\/Interspeech.2016-1557"},{"key":"9591_CR35","first-page":"175","volume":"2","author":"L Kerkeni","year":"2018","unstructured":"Kerkeni L, Serrestou Y, Mbarki M, Raoof K, Mahjoub MA (2018) Speech emotion recognition Methods and cases study. In ICAART 2:175\u2013182","journal-title":"In ICAART"},{"key":"9591_CR36","doi-asserted-by":"crossref","unstructured":"Khan A, Roy UK (2017) Emotion recognition using prosodie and spectral features of speech and na\u00efve bayes classifier. In: 2017 international conference on wireless communications, signal processing and networking (WiSPNET), pages 1017\u20131021. IEEE","DOI":"10.1109\/WiSPNET.2017.8299916"},{"key":"9591_CR37","unstructured":"Kim J, Englebienne G, Truong KP, Evers V (2017). arXiv:1708.03920"},{"issue":"1","key":"9591_CR38","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/s10772-020-09672-4","volume":"23","author":"A Koduru","year":"2020","unstructured":"Koduru A, Valiveti HB, Budati AK (2020) Feature extraction algorithms to improve the speech emotion recognition rate. International Journal of Speech Technology 23(1):45\u201355","journal-title":"International Journal of Speech Technology"},{"issue":"4","key":"9591_CR39","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1007\/s10772-016-9358-0","volume":"19","author":"S Kuchibhotla","year":"2016","unstructured":"Kuchibhotla S, Vankayalapati HD, Anne Koteswara R (2016) An optimal two stage feature selection for speech emotion recognition using acoustic features. International Journal of Speech Technology 19(4):657\u2013667","journal-title":"International Journal of Speech Technology"},{"issue":"6","key":"9591_CR40","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1016\/j.sigpro.2004.03.004","volume":"84","author":"O-W Kwon","year":"2004","unstructured":"Kwon O-W, Lee T-W (2004) Phoneme recognition using ica-based feature extraction and transformation. Signal Process 84(6):1005\u20131019","journal-title":"Signal Process"},{"key":"9591_CR41","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.procs.2015.10.020","volume":"70","author":"S Lalitha","year":"2015","unstructured":"Lalitha S, Geyasruti D, Narayanan R, Shravani M (2015) Emotion detection using mfcc and cepstrum features. Procedia Computer Science 70:29\u201335","journal-title":"Procedia Computer Science"},{"key":"9591_CR42","doi-asserted-by":"crossref","unstructured":"Li L, Zhao Y, Jiang D, Zhang Y, Wang F, Gonzalez I, Valentin E, Sahli H (2013) Hybrid deep neural network-hidden markov model (dnn-hmm) based speech emotion recognition. In: Affective Computing and Intelligent Interaction ACII Hybrid deep neural network\u2013hidden markov Humaine Association Conference on, pages 312\u2013317 IEEE, p 2013","DOI":"10.1109\/ACII.2013.58"},{"key":"9591_CR43","doi-asserted-by":"crossref","unstructured":"Likitha MS, Gupta SRR, Hasitha K, Raju AU (2017) Speech based human emotion recognition using mfcc. In: 2017 international conference on wireless communications, signal processing and networking (WiSPNET), pages 2257\u20132260. IEEE","DOI":"10.1109\/WiSPNET.2017.8300161"},{"key":"9591_CR44","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, Min W, 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":"9591_CR45","doi-asserted-by":"crossref","unstructured":"Lotfidereshgi R, Gournay P (2017) Biologically inspired speech emotion recognition. In: 2017 IEEE International Conference On Acoustics, Speech and Signal Processing (ICASSP), pages 5135\u20135139 IEEE","DOI":"10.1109\/ICASSP.2017.7953135"},{"key":"9591_CR46","doi-asserted-by":"crossref","unstructured":"Lugger M, Yang B (2008) Cascaded emotion classification via psychological emotion dimensions using a large set of voice quality parameters. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pages 4945\u20134948 IEEE","DOI":"10.1109\/ICASSP.2008.4518767"},{"issue":"3","key":"9591_CR47","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1016\/j.csl.2013.08.004","volume":"28","author":"A Milton","year":"2014","unstructured":"Milton A, Tamil SS (2014) Class-specific multiple classifiers scheme to recognize emotions from speech signals. Computer Speech & Language 28(3):727\u2013742","journal-title":"Computer Speech & Language"},{"key":"9591_CR48","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.dsp.2015.11.004","volume":"49","author":"SM Mirhassani","year":"2016","unstructured":"Mirhassani SM, Ting HN, Gharahbagh AA (2016) Fuzzy decision fusion of complementary experts based on evolutionary cepstral coefficients for phoneme recognition. Digital Signal Processing 49:116\u2013125","journal-title":"Digital Signal Processing"},{"key":"9591_CR49","doi-asserted-by":"crossref","unstructured":"Pohjalainen J, Alku P (2014) Multi-scale modulation filtering in automatic detection of emotions in telephone speech. In: IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP pages 980\u2013984 IEEE","DOI":"10.1109\/ICASSP.2014.6853743"},{"key":"9591_CR50","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1109\/34.75512","volume":"3","author":"SJ Raudys","year":"1991","unstructured":"Raudys SJ, Jain AK (1991) Small sample size effects in statistical pattern recognition Recommendations for practitioners. IEEE Transactions on Pattern Analysis & Machine Intelligence 3:252\u2013264","journal-title":"IEEE Transactions on Pattern Analysis & Machine Intelligence"},{"key":"9591_CR51","unstructured":"Sreenivasa R, Koolagudi K , Shashidhar G (2012) Emotion recognition using speech features Springer Science & Business Media"},{"key":"9591_CR52","unstructured":"Sreenivasa Rao, Koolagudi K , Shashidhar G (2013) Robust emotion recognition using spectral and prosodic features Springer Science & Business Media"},{"key":"9591_CR53","doi-asserted-by":"crossref","unstructured":"Scherer S, Schwenker F, Palm G (2007) Classifier fusion for emotion recognition from speech","DOI":"10.1049\/cp:20070360"},{"key":"9591_CR54","doi-asserted-by":"crossref","unstructured":"Schuller B, Batliner A, Seppi D, Steidl S, Vogt T, Wagner J, Devillers L, Vidrascu L, Amir N, Kessousm L, et al. (2007) The relevance of feature type for the automatic classification of emotional user states: low level descriptors and functionals. In: Eighth Annual Conference of the International Speech Communication Association","DOI":"10.21437\/Interspeech.2007-612"},{"issue":"4","key":"9591_CR55","doi-asserted-by":"crossref","first-page":"91","DOI":"10.3390\/computers8040091","volume":"8","author":"S Sekkate","year":"2019","unstructured":"Sekkate S, Khalil M, Adib A, Jebara SB (2019) An investigation of a feature-level fusion for noisy speech emotion recognition. Computers 8 (4):91","journal-title":"Computers"},{"key":"9591_CR56","doi-asserted-by":"crossref","unstructured":"Semwal N, Kumar A, Sakthivel N (2017) Automatic speech emotion detection system using multi-domain acoustic feature selection Classification models.. In: IEEE International Conference on Identity, Security and Behavior Analysis ISBA pages 1\u20136 IEEE, p 2017","DOI":"10.1109\/ISBA.2017.7947681"},{"issue":"Sup. 1","key":"9591_CR57","doi-asserted-by":"crossref","first-page":"2056","DOI":"10.3906\/elk-1302-90","volume":"23","author":"A Shahzadi","year":"2015","unstructured":"Shahzadi A, Ahmadyfard A, Harimi A, Yaghmaie K (2015) Speech emotion recognition using nonlinear dynamics features. Turkish Journal of Electrical Engineering & Computer Sciences 23(Sup. 1):2056\u20132073","journal-title":"Turkish Journal of Electrical Engineering & Computer Sciences"},{"issue":"2","key":"9591_CR58","first-page":"140","volume":"26","author":"A Shahzadi","year":"2013","unstructured":"Shahzadi A, Ahmadyfard A, Yaghmaie K, Harimi A (2013) Recognition of emotion in speech using spectral patterns. Malaysian Journal of Computer Science 26(2):140\u2013158","journal-title":"Malaysian Journal of Computer Science"},{"key":"9591_CR59","doi-asserted-by":"crossref","unstructured":"Shirani A, 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"},{"key":"9591_CR60","doi-asserted-by":"crossref","unstructured":"Sinith MS, Aswathi E, Deepa TM, Shameema CP, Rajan S (2015) Emotion recognition from audio signals using support vector machine. In: 2015 IEEE Recent Advances Intelligent Computational Systems RAICS pages 139\u2013144 IEEE","DOI":"10.1109\/RAICS.2015.7488403"},{"key":"9591_CR61","doi-asserted-by":"crossref","unstructured":"Skowronski MD, Harris JG (2002) Increased mfcc filter bandwidth for noise-robust phoneme recognition. In: Acoustics Speech an Signal Processing ICASSP IEEE International Conference on, volume 1, pages I\u2013801 IEEE","DOI":"10.1109\/ICASSP.2002.5743839"},{"key":"9591_CR62","unstructured":"Slaney M (1998) Auditory toolbox. Interval Research Corporation, Tech Rep 10(1998)"},{"issue":"4","key":"9591_CR63","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1250\/ast.23.195","volume":"23","author":"BH Story","year":"2002","unstructured":"Story BH (2002) An overview of the physiology, physics and modeling of the sound source for vowels. Acoust Sci Technol 23(4):195\u2013206","journal-title":"Acoust Sci Technol"},{"issue":"6","key":"9591_CR64","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. Multimedia Tools and Applications 76(6):8305\u20138328","journal-title":"Multimedia Tools and Applications"},{"key":"9591_CR65","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.bspc.2014.10.008","volume":"18","author":"Y Sun","year":"2015","unstructured":"Sun Y, Wen G, Wang J (2015) Weighted spectral features based on local hu moments for speech emotion recognition. Biomedical Signal Processing and Control 18:80\u201390","journal-title":"Biomedical Signal Processing and Control"},{"key":"9591_CR66","unstructured":"Toolkit HMM (2002) Version 3.2, Cambridge University Engineering Department, Cambridge UK (2002)"},{"key":"9591_CR67","doi-asserted-by":"crossref","unstructured":"Trigeorgis G, Ringeval F, Brueckner R, Marchi E, Nicolaou MA, Schuller B, Zafeiriou S (2016) Adieu features? end-to-end speech emotion recognition using a deep convolutional recurrent network. In: Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on, pages 5200\u20135204. IEEE","DOI":"10.1109\/ICASSP.2016.7472669"},{"issue":"4","key":"9591_CR68","doi-asserted-by":"crossref","first-page":"3419","DOI":"10.1016\/j.asoc.2011.01.012","volume":"11","author":"LD Vignolo","year":"2011","unstructured":"Vignolo LD, Rufiner HL, Milone DH, Goddard JC (2011) Evolutionary cepstral coefficients. Appl Soft Comput 11(4):3419\u20133428","journal-title":"Appl Soft Comput"},{"key":"9591_CR69","doi-asserted-by":"crossref","unstructured":"Vlasenko B, Schuller B, Wendemuth A, Rigoll G (2007) Combining frame and turn-level information for robust recognition of emotions within speech. In: Proc. INTERSPEECH Combining Antwerp, Belgium","DOI":"10.21437\/Interspeech.2007-611"},{"key":"9591_CR70","doi-asserted-by":"crossref","unstructured":"Wen G, Li H, Huang J, Li D, Xun E (2017) Random deep belief networks for recognizing emotions from speech signals","DOI":"10.1155\/2017\/1945630"},{"issue":"5","key":"9591_CR71","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1016\/j.specom.2010.08.013","volume":"53","author":"S Wu","year":"2011","unstructured":"Wu S, Falk TH, Chan W-Y (2011) Automatic speech emotion recognition using modulation spectral features. Speech Comm 53(5):768\u2013785","journal-title":"Speech Comm"},{"issue":"1","key":"9591_CR72","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":"9591_CR73","doi-asserted-by":"crossref","first-page":"2345","DOI":"10.1007\/s11042-018-6329-2","volume":"78","author":"S-A Yoon","year":"2019","unstructured":"Yoon S-A, Son G, Kwon S (2019) Fear emotion classification in speech by acoustic and behavioral cues. Multimedia Tools and Applications 78 (2):2345\u20132366","journal-title":"Multimedia Tools and Applications"},{"key":"9591_CR74","doi-asserted-by":"crossref","unstructured":"Y\u00fcnc\u00fc E, Hacihabiboglu H, Bozsahin C (2014) Automatic speech emotion recognition using auditory models with binary decision tree and svm. In: 2014 22nd International Conference on Pattern Recognition, pages 773\u2013778. IEEE","DOI":"10.1109\/ICPR.2014.143"},{"key":"9591_CR75","doi-asserted-by":"crossref","unstructured":"Zaidan NA, Salam MS (2016) Mfcc global features selection in improving speech emotion recognition rate. In: Advances in machine learning and signal processing, pages 141\u2013153. Springer International Publishing, Cham","DOI":"10.1007\/978-3-319-32213-1_13"},{"issue":"5","key":"9591_CR76","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, Ros\u00e2ngela C (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"},{"issue":"6","key":"9591_CR77","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"},{"issue":"2","key":"9591_CR78","doi-asserted-by":"crossref","first-page":"114","DOI":"10.5772\/55403","volume":"10","author":"S Zhang","year":"2013","unstructured":"Zhang S, Zhao X, Lei B (2013) Speech emotion recognition using an enhanced kernel isomap for human-robot interaction. Int J Adv Robot Syst 10(2):114","journal-title":"Int J Adv Robot Syst"},{"issue":"12","key":"9591_CR79","doi-asserted-by":"crossref","first-page":"2528","DOI":"10.1109\/TMM.2016.2598092","volume":"18","author":"T Zhang","year":"2016","unstructured":"Zhang T, Zheng W, Cui Z, Zong Y, Yan J, Yan K (2016) A deep neural network-driven feature learning method for multi-view facial expression recognition. IEEE Transactions on Multimedia 18(12):2528\u20132536","journal-title":"IEEE Transactions on Multimedia"},{"key":"9591_CR80","doi-asserted-by":"crossref","unstructured":"Zhang Z, Wu B, Schuller B (2019) Attention-augmented end-to-end multi-task learning for emotion prediction from speech. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 6705\u20136709. IEEE","DOI":"10.1109\/ICASSP.2019.8682896"},{"key":"9591_CR81","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.bspc.2018.08.035","volume":"47","author":"J Zhao","year":"2019","unstructured":"Zhao J, Mao X, Chen L (2019) Speech emotion recognition using deep 1d & 2d cnn lstm networks. Biomedical Signal Processing and Control 47:312\u2013323","journal-title":"Biomedical Signal Processing and Control"},{"key":"9591_CR82","doi-asserted-by":"crossref","unstructured":"Zhou X, Guo J, Bie R (2016) Deep learning based affective model for speech emotion recognition. In: Ubiquitous Intelligence & Computing, Advanced and Trusted Computing, Scalable Computing and Communications Cloud and Big Data Computing, Internet of People, and Smart World Congress UIC\/ATC\/ScalCom\/CBDCom\/IoP\/SmartWorld 2016 Intl IEEE Conferences, pages 841\u2013846. IEEE","DOI":"10.1109\/UIC-ATC-ScalCom-CBDCom-IoP-SmartWorld.2016.0133"},{"issue":"2","key":"9591_CR83","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1121\/1.1908630","volume":"33","author":"E Zwicker","year":"1961","unstructured":"Zwicker E (1961) Subdivision of the audible frequency range into critical bands (frequenzgruppen). The Journal of the Acoustical Society of America 33 (2):248\u2013248","journal-title":"The Journal of the Acoustical Society of America"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09591-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-09591-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09591-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,19]],"date-time":"2022-11-19T00:43:11Z","timestamp":1668818591000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-09591-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,18]]},"references-count":83,"journal-issue":{"issue":"47-48","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["9591"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-09591-1","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2020,9,18]]},"assertion":[{"value":"18 June 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}