{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:26:50Z","timestamp":1775068010413,"version":"3.50.1"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T00:00:00Z","timestamp":1701820800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T00:00:00Z","timestamp":1701820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s00034-023-02544-7","type":"journal-article","created":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T10:02:19Z","timestamp":1701856939000},"page":"2224-2250","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Hilbert Domain Analysis of Wavelet Packets for Emotional Speech Classification"],"prefix":"10.1007","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0654-782X","authenticated-orcid":false,"given":"Biswajit","family":"Karan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arvind","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,6]]},"reference":[{"issue":"4","key":"2544_CR1","doi-asserted-by":"publisher","first-page":"1249","DOI":"10.3390\/s21041249","volume":"21","author":"BJ Abbaschian","year":"2021","unstructured":"B.J. Abbaschian, D. Sierra-Sosa, A. Elmaghraby, Deep learning techniques for speech emotion recognition, from databases to models. Sensors 21(4), 1249 (2021)","journal-title":"Sensors"},{"key":"2544_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108046","volume":"179","author":"J Ancilin","year":"2021","unstructured":"J. Ancilin, A. Milton, Improved speech emotion recognition with Mel frequency magnitude coefficient. Appl. Acoust. 179, 108046 (2021)","journal-title":"Appl. Acoust."},{"issue":"4","key":"2544_CR3","doi-asserted-by":"publisher","first-page":"15","DOI":"10.3991\/ijoe.v16i04.11870","volume":"16","author":"G Assun\u00e7\u00e3o","year":"2020","unstructured":"G. Assun\u00e7\u00e3o, P. Menezes, F. Perdig\u00e3o, Speaker awareness for speech emotion recognition. Int. J. Online Biomed. Eng. 16(4), 15\u201322 (2020). https:\/\/doi.org\/10.3991\/ijoe.v16i04.11870","journal-title":"Int. J. Online Biomed. Eng."},{"key":"2544_CR4","doi-asserted-by":"publisher","unstructured":"X. Cai, D. Dai, Z. Wu, X. Li, J. Li & H. Meng (2021) Emotion controllable speech synthesis using emotion-unlabeled dataset with the assistance of cross-domain speech emotion recognition. In:\u00a0ICASSP 2021\u20132021 IEEE international conference on acoustics, speech and signal processing (ICASSP)\u00a0(pp. 5734\u20135738). IEEE. https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9413907","DOI":"10.1109\/ICASSP39728.2021.9413907"},{"key":"2544_CR5","doi-asserted-by":"publisher","unstructured":"S. Casale, A. Russo, G. Scebba & S. Serrano (2008) Speech emotion classification using machine learning algorithms. In:\u00a02008 IEEE international conference on semantic computing\u00a0(pp. 158\u2013165). IEEE. https:\/\/doi.org\/10.1109\/ICSC.2008.43","DOI":"10.1109\/ICSC.2008.43"},{"issue":"20","key":"2544_CR6","first-page":"6","volume":"1","author":"Y Chavhan","year":"2010","unstructured":"Y. Chavhan, M.L. Dhore, P. Yesaware, Speech emotion recognition using support vector machine. Int. J. Comput. Appl. 1(20), 6\u20139 (2010)","journal-title":"Int. J. Comput. Appl."},{"key":"2544_CR7","doi-asserted-by":"publisher","unstructured":"X. Cheng, & Q. Duan (2012) Speech emotion recognition using gaussian mixture model. In:\u00a02012 international conference on computer application and system modeling\u00a0(pp. 1222\u20131225). Atlantis Press. https:\/\/doi.org\/10.2991\/iccasm.2012.311","DOI":"10.2991\/iccasm.2012.311"},{"key":"2544_CR8","unstructured":"G. Costantini, I. Iaderola, A. Paoloni, & M. Todisco (2014) EMOVO corpus: an Italian emotional speech database. In:\u00a0Proceedings of the ninth international conference on language resources and evaluation (LREC'14)\u00a0(pp. 3501\u20133504). European Language Resources Association (ELRA)"},{"key":"2544_CR9","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/s11257-007-9037-6","volume":"18","author":"SK Dmello","year":"2008","unstructured":"S.K. Dmello, S.D. Craig, A. Witherspoon, B. McDaniel, A. Graesser, Automatic detection of learner\u2019s affect from conversational cues. User Model. User-Adapt. Interact. 18, 45\u201380 (2008)","journal-title":"User Model. User-Adapt. Interact."},{"issue":"3","key":"2544_CR10","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1109\/TCYB.2017.2787717","volume":"49","author":"S Deb","year":"2018","unstructured":"S. Deb, S. Dandapat, Multiscale amplitude feature and significance of enhanced vocal tract information for emotion classification. IEEE Trans. Cybernet. 49(3), 802\u2013815 (2018)","journal-title":"IEEE Trans. Cybernet."},{"issue":"1","key":"2544_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10772-012-9142-8","volume":"16","author":"VN Degaonkar","year":"2013","unstructured":"V.N. Degaonkar, S.D. Apte, Emotion modeling from speech signal based on wavelet packet transform. Int. J. Speech Technol. 16(1), 1\u20135 (2013)","journal-title":"Int. J. Speech Technol."},{"key":"2544_CR12","doi-asserted-by":"publisher","first-page":"4299","DOI":"10.1109\/ACCESS.2016.2591442","volume":"4","author":"J Deng","year":"2016","unstructured":"J. Deng, X. Xu, Z. Zhang, S. Fr\u00fchholz, B. Schuller, Exploitation of phase-based features for whispered speech emotion recognition. IEEE Access 4, 4299\u20134309 (2016)","journal-title":"IEEE Access"},{"issue":"2","key":"2544_CR13","doi-asserted-by":"publisher","first-page":"113","DOI":"10.18034\/abcjar.v5i2.550","volume":"5","author":"A Ganapathy","year":"2016","unstructured":"A. Ganapathy, Speech emotion recognition using deep learning techniques. ABC J. Adv. Res. 5(2), 113\u2013122 (2016)","journal-title":"ABC J. Adv. Res."},{"key":"2544_CR14","first-page":"1916","volume":"2013","author":"P Gangamohan","year":"2013","unstructured":"P. Gangamohan, S.R. Kadiri, B. Yegnanarayana, Analysis of emotional speech at subsegmental level. Interspeech 2013, 1916\u20131920 (2013)","journal-title":"Interspeech"},{"key":"2544_CR15","unstructured":"J. Goldberger, G.E. Hinton, S. Roweis, R.R. Salakhutdinov, Neighbourhood components analysis.\u00a0Adv. Neural Inform. Process. Syst. (2004). http:\/\/api.semanticscholar.org\/CorpusID:8616518"},{"issue":"1","key":"2544_CR16","first-page":"12","volume":"6","author":"TS Gunawan","year":"2018","unstructured":"T.S. Gunawan, M.F. Alghifari, M.A. Morshidi, M. Kartiwi, A review on emotion recognition algorithms using speech analysis Indonesian. J. Electric. Eng. Inform. (IJEEI) 6(1), 12\u201320 (2018)","journal-title":"J. Electric. Eng. Inform. (IJEEI)"},{"key":"2544_CR17","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.specom.2021.11.005","volume":"136","author":"L Guo","year":"2022","unstructured":"L. Guo, L. Wang, J. Dang, E.S. Chng, S. Nakagawa, Learning affective representations based on magnitude and dynamic relative phase information for speech emotion recognition. Speech Commun. 136, 118\u2013127 (2022)","journal-title":"Speech Commun."},{"key":"2544_CR18","doi-asserted-by":"publisher","first-page":"101119","DOI":"10.1016\/j.csl.2020.101119","volume":"65","author":"F Haider","year":"2021","unstructured":"F. Haider, S. Pollak, P. Albert, S. Luz, Emotion recognition in low-resource settings: an evaluation of automatic feature selection methods. Comput. Speech Language 65, 101119 (2021)","journal-title":"Comput. Speech Language"},{"key":"2544_CR19","doi-asserted-by":"publisher","unstructured":"K. Han, D. Yu, I. Tashev, Speech emotion recognition using deep neural network and extreme learning machine. In:\u00a0Interspeech 2014. (2014). https:\/\/doi.org\/10.21437\/Interspeech.2014-57","DOI":"10.21437\/Interspeech.2014-57"},{"issue":"1","key":"2544_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13638-018-1253-8","volume":"2018","author":"T Han","year":"2018","unstructured":"T. Han, J. Zhang, Z. Zhang, G. Sun, L. Ye, H. Ferdinando, S. Yang, Emotion recognition and school violence detection from children speech. EURASIP J. Wirel. Commun. Netw. 2018(1), 1\u201310 (2018)","journal-title":"EURASIP J. Wirel. Commun. Netw."},{"key":"2544_CR21","doi-asserted-by":"crossref","unstructured":"Z. M. Hira, D. F. Gillies (2015) A review of feature selection and feature extraction methods applied on microarray data.\u00a0Adv. Bioinform.\u00a02015","DOI":"10.1155\/2015\/198363"},{"key":"2544_CR22","doi-asserted-by":"publisher","first-page":"61672","DOI":"10.1109\/ACCESS.2020.2984368","volume":"8","author":"NH Ho","year":"2020","unstructured":"N.H. Ho, H.J. Yang, S.H. Kim, G. Lee, Multimodal approach of speech emotion recognition using multi-level multi-head fusion attention-based recurrent neural network. IEEE Access 8, 61672\u201361686 (2020)","journal-title":"IEEE Access"},{"key":"2544_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.101894","volume":"59","author":"D Issa","year":"2020","unstructured":"D. Issa, M.F. Demirci, A. Yazici, Speech emotion recognition with deep convolutional neural networks. Biomed. Signal Process. Control 59, 101894 (2020)","journal-title":"Biomed. Signal Process. Control"},{"key":"2544_CR24","first-page":"1","volume":"80","author":"R Jahangir","year":"2021","unstructured":"R. Jahangir, Y.W. Teh, F. Hanif, G. Mujtaba, Deep learning approaches for speech emotion recognition: state of the art and research challenges. Multimed. Tools Appl. 80, 1\u201368 (2021)","journal-title":"Multimed. Tools Appl."},{"key":"2544_CR25","doi-asserted-by":"crossref","unstructured":"C. Joesph, A. Rajeswari, B. Premalatha, & C. Balapriya (2020) Implementation of physiological signal based emotion recognition algorithm. In\u00a02020 IEEE 36th international conference on data engineering (ICDE)\u00a0(pp. 2075\u20132079). IEEE","DOI":"10.1109\/ICDE48307.2020.9153878"},{"issue":"9","key":"2544_CR26","doi-asserted-by":"publisher","first-page":"4459","DOI":"10.1007\/s00034-020-01377-y","volume":"39","author":"SR Kadiri","year":"2020","unstructured":"S.R. Kadiri, P. Gangamohan, S.V. Gangashetty, P. Alku, B. Yegnanarayana, Excitation features of speech for emotion recognition using neutral speech as reference. Circ. Syst. Signal Process. 39(9), 4459\u20134481 (2020)","journal-title":"Circ. Syst. Signal Process."},{"issue":"2","key":"2544_CR27","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1016\/j.bbe.2022.04.003","volume":"42","author":"B Karan","year":"2022","unstructured":"B. Karan, S.S. Sahu, J.R. Orozco-Arroyave, An investigation about the relationship between dysarthria level of speech and the neurological state of Parkinson\u2019s patients. Biocybernet. Biomed. Eng. 42(2), 710\u2013726 (2022)","journal-title":"Biocybernet. Biomed. Eng."},{"key":"2544_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102050","volume":"61","author":"B Karan","year":"2020","unstructured":"B. Karan, S.S. Sahu, J.R. Orozco-Arroyave, K. Mahto, Hilbert spectrum analysis for automatic detection and evaluation of Parkinson\u2019s speech. Biomed. Signal Process. Control 61, 102050 (2020)","journal-title":"Biomed. Signal Process. Control"},{"key":"2544_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101216","volume":"69","author":"B Karan","year":"2021","unstructured":"B. Karan, S.S. Sahu, J.R. Orozco-Arroyave, K. Mahto, Non-negative matrix factorization-based time-frequency feature extraction of voice signal for Parkinson\u2019s disease prediction. Comput. Speech Lang. 69, 101216 (2021)","journal-title":"Comput. Speech Lang."},{"key":"2544_CR30","doi-asserted-by":"crossref","unstructured":"L. Kerkeni, Y. Serrestou, M. Mbarki, K. Raoof, M. A. Mahjoub & C. Cleder (2019). Automatic speech emotion recognition using machine learning","DOI":"10.5772\/intechopen.84856"},{"key":"2544_CR31","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s10772-012-9150-8","volume":"15","author":"SG Koolagudi","year":"2012","unstructured":"S.G. Koolagudi, S.R. Krothapalli, Emotion recognition from speech using sub-syllabic and pitch synchronous spectral features. Int. J. Speech Technol. 15, 495\u2013511 (2012)","journal-title":"Int. J. Speech Technol."},{"key":"2544_CR32","doi-asserted-by":"publisher","first-page":"1919","DOI":"10.1007\/s40747-021-00295-z","volume":"7","author":"PT Krishnan","year":"2021","unstructured":"P.T. Krishnan, A.N. Joseph Raj, V. Rajangam, Emotion classification from speech signal based on empirical mode decomposition and non-linear features: speech emotion recognition. Complex Intell. Syst. 7, 1919\u20131934 (2021)","journal-title":"Complex Intell. Syst."},{"issue":"1","key":"2544_CR33","doi-asserted-by":"publisher","first-page":"646","DOI":"10.14704\/WEB\/V19I1\/WEB19046","volume":"19","author":"T Kumar","year":"2022","unstructured":"T. Kumar, S.S. Rajest, K.O. Villalba-Condori, D. Arias-Chavez, K. Rajesh, M.K. Chakravarthi, An evaluation on speech recognition technology based on machine learning. Webology 19(1), 646\u2013663 (2022)","journal-title":"Webology"},{"issue":"1","key":"2544_CR34","doi-asserted-by":"publisher","first-page":"183","DOI":"10.3390\/s20010183","volume":"20","author":"S Kwon","year":"2019","unstructured":"S. Kwon, A CNN-assisted enhanced audio signal processing for speech emotion recognition. Sensors 20(1), 183 (2019)","journal-title":"Sensors"},{"issue":"9","key":"2544_CR35","doi-asserted-by":"publisher","first-page":"5116","DOI":"10.1002\/int.22505","volume":"36","author":"S Kwon","year":"2021","unstructured":"S. Kwon, Optimal feature selection based speech emotion recognition using two-stream deep convolutional neural network. Int. J. Intell. Syst. 36(9), 5116\u20135135 (2021)","journal-title":"Int. J. Intell. Syst."},{"key":"2544_CR36","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.neucom.2017.07.050","volume":"273","author":"ZT Liu","year":"2018","unstructured":"Z.T. Liu, M. Wu, W.H. Cao, J.W. Mao, J.P. Xu, G.Z. Tan, Speech emotion recognition based on feature selection and extreme learning machine decision tree. Neurocomputing 273, 271\u2013280 (2018)","journal-title":"Neurocomputing"},{"key":"2544_CR37","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1007\/s10772-018-09572-8","volume":"22","author":"S Lalitha","year":"2019","unstructured":"S. Lalitha, S. Tripathi, D. Gupta, Enhanced speech emotion detection using deep neural networks. Int. J. Speech Technol. 22, 497\u2013510 (2019)","journal-title":"Int. J. Speech Technol."},{"key":"2544_CR38","doi-asserted-by":"crossref","unstructured":"S. Latif, R. Rana, S. Younis, J. Qadir, & J. Epps (2018) Transfer learning for improving speech emotion classification accuracy.\u00a0arXiv preprint arXiv:1801.06353","DOI":"10.21437\/Interspeech.2018-1625"},{"issue":"9\u201310","key":"2544_CR39","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1016\/j.specom.2011.06.004","volume":"53","author":"CC Lee","year":"2011","unstructured":"C.C. Lee, E. Mower, C. Busso, S. Lee, S. Narayanan, Emotion recognition using a hierarchical binary decision tree approach. Speech Commun. 53(9\u201310), 1162\u20131171 (2011)","journal-title":"Speech Commun."},{"issue":"10","key":"2544_CR40","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.3390\/electronics10101163","volume":"10","author":"E Lieskovsk\u00e1","year":"2021","unstructured":"E. Lieskovsk\u00e1, M. Jakubec, R. Jarina, M. Chmul\u00edk, A review on speech emotion recognition using deep learning and attention mechanism. Electronics 10(10), 1163 (2021)","journal-title":"Electronics"},{"key":"2544_CR41","doi-asserted-by":"crossref","unstructured":"D. Litman, & K. Forbes-Riley (2004) Predicting student emotions in computer-human tutoring dialogues. In:\u00a0Proceedings of the 42nd annual meeting of the association for computational linguistics (ACL-04)\u00a0(pp. 351\u2013358)","DOI":"10.3115\/1218955.1219000"},{"issue":"2","key":"2544_CR42","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/s10772-021-09955-4","volume":"25","author":"M Liu","year":"2022","unstructured":"M. Liu, English speech emotion recognition method based on speech recognition. Int. J. Speech Technol. 25(2), 391\u2013398 (2022)","journal-title":"Int. J. Speech Technol."},{"key":"2544_CR43","doi-asserted-by":"crossref","unstructured":"W. Liu, W. L. Zheng, & B. L. Lu (2016) Emotion recognition using multimodal deep learning. In\u00a0Neural information processing: 23rd international conference, ICONIP 2016, Kyoto, Japan, Oct 16\u201321, 2016, Proceedings, Part II 23\u00a0(pp. 521\u2013529). Springer International Publishing","DOI":"10.1007\/978-3-319-46672-9_58"},{"key":"2544_CR44","doi-asserted-by":"crossref","unstructured":"T. L. Nwe, F. S. Wei, & L. C. De Silva (2001) Speech based emotion classification. In\u00a0Proceedings of IEEE region 10 international conference on electrical and electronic technology. TENCON 2001 (Cat. No. 01CH37239)\u00a0(Vol. 1, pp. 297\u2013301). IEEE","DOI":"10.1109\/TENCON.2001.949600"},{"key":"2544_CR45","doi-asserted-by":"crossref","unstructured":"S. Olhede, & A. T. Walden (2004) The Hilbert spectrum via wavelet projections.In: Proceedings of the royal society of London. Series A: mathematical, physical and engineering sciences,\u00a0460(2044), 955\u2013975","DOI":"10.1098\/rspa.2003.1199"},{"key":"2544_CR46","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.apacoust.2018.11.028","volume":"146","author":"T \u00d6zseven","year":"2019","unstructured":"T. \u00d6zseven, A novel feature selection method for speech emotion recognition. Appl. Acoust. 146, 320\u2013326 (2019)","journal-title":"Appl. Acoust."},{"key":"2544_CR47","doi-asserted-by":"crossref","unstructured":"R. Pappagari, J. Villalba, P. \u017belasko, L. Moro-Velazquez & N. Dehak (2021). Copypaste: an augmentation method for speech emotion recognition. In\u00a0ICASSP 2021\u20132021 IEEE international conference on acoustics, speech and signal processing (ICASSP)\u00a0(pp. 6324\u20136328). IEEE. [43]","DOI":"10.1109\/ICASSP39728.2021.9415077"},{"key":"2544_CR48","doi-asserted-by":"crossref","unstructured":"Percival, B. Donald, and T. Andrew Walden.\u00a0Wavelet methods for time series analysis. Vol. 4. Cambridge university press, 2000","DOI":"10.1017\/CBO9780511841040"},{"key":"2544_CR49","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1007\/s11235-011-9624-z","volume":"52","author":"S Ramakrishnan","year":"2013","unstructured":"S. Ramakrishnan, I.M. El Emary, Speech emotion recognition approaches in human computer interaction. Telecommun. Syst. 52, 1467\u20131478 (2013)","journal-title":"Telecommun. Syst."},{"key":"2544_CR50","doi-asserted-by":"crossref","first-page":"1","DOI":"10.14716\/ijtech.v12i1.4691","volume":"12","author":"S Ramesh","year":"2021","unstructured":"S. Ramesh, S. Gomathi, S. Sasikala, T.R. Saravanan, Automatic speech emotion detection using hybrid of gray wolf optimizer and na\u00efve Bayes. Int. J. Speech Technol. 12, 1\u20138 (2021)","journal-title":"Int. J. Speech Technol."},{"key":"2544_CR51","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s10772-012-9172-2","volume":"16","author":"KS Rao","year":"2013","unstructured":"K.S. Rao, S.G. Koolagudi, R.R. Vempada, Emotion recognition from speech using global and local prosodic features. Int. J. Speech Technol. 16, 143\u2013160 (2013)","journal-title":"Int. J. Speech Technol."},{"key":"2544_CR52","doi-asserted-by":"publisher","first-page":"2056","DOI":"10.3906\/elk-1302-90","volume":"23","author":"A Shahzadi","year":"2015","unstructured":"A. Shahzadi, A. Ahmadyfard, A. Harimi, K. Yaghmaie, Speech emotion recognition using nonlinear dynamics features. Turk. J. Electric. Eng. Comput. Sci. 23, 2056 (2015)","journal-title":"Turk. J. Electric. Eng. Comput. Sci."},{"key":"2544_CR53","doi-asserted-by":"crossref","unstructured":"P. Shen, Z. Changjun, & X. Chen (2011) Automatic speech emotion recognition using support vector machine. In\u00a0Proceedings of 2011 international conference on electronic & mechanical engineering and information technology\u00a0(Vol. 2, pp. 621\u2013625). IEEE","DOI":"10.1109\/EMEIT.2011.6023178"},{"key":"2544_CR54","doi-asserted-by":"crossref","unstructured":"M. Sidorov, S. Ultes, & A. Schmitt (2014) Emotions are a personal thing: Towards speaker-adaptive emotion recognition. In\u00a02014 IEEE international conference on acoustics, speech and signal processing (ICASSP)\u00a0(pp. 4803\u20134807). IEEE","DOI":"10.1109\/ICASSP.2014.6854514"},{"issue":"5","key":"2544_CR55","doi-asserted-by":"publisher","first-page":"4237","DOI":"10.1007\/s40747-022-00713-w","volume":"8","author":"M Swain","year":"2022","unstructured":"M. Swain, B. Maji, P. Kabisatpathy, A. Routray, A DCRNN-based ensemble classifier for speech emotion recognition in Odia language. Complex Intell. Syst. 8(5), 4237\u20134249 (2022)","journal-title":"Complex Intell. Syst."},{"issue":"1","key":"2544_CR56","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s13636-021-00208-5","volume":"2021","author":"D Tang","year":"2021","unstructured":"D. Tang, P. Kuppens, L. Geurts, T. van Waterschoot, End-to-end speech emotion recognition using a novel context-stacking dilated convolution neural network. EURASIP J. Audio Speech Music Process. 2021(1), 18 (2021)","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"2544_CR57","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1007\/s11633-019-1175-x","volume":"16","author":"JH Tao","year":"2019","unstructured":"J.H. Tao, J. Huang, Y. Li, Z. Lian, M.Y. Niu, Semi-supervised ladder networks for speech emotion recognition. Int. J. Autom. Comput. 16, 437\u2013448 (2019)","journal-title":"Int. J. Autom. Comput."},{"key":"2544_CR58","doi-asserted-by":"crossref","unstructured":"K. Tarunika, R. B. Pradeeba, & P. Aruna (2018). Applying machine learning techniques for speech emotion recognition. In\u00a02018 9th international conference on computing, communication and networking technologies (ICCCNT)\u00a0(pp. 1\u20135). IEEE","DOI":"10.1109\/ICCCNT.2018.8494104"},{"issue":"6","key":"2544_CR59","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1016\/j.measurement.2007.07.007","volume":"41","author":"W Ting","year":"2008","unstructured":"W. Ting, Y. Guo-Zheng, Y. Bang-Hua, S. Hong, EEG feature extraction based on wavelet packet decomposition for brain computer interface. Measurement 41(6), 618\u2013625 (2008)","journal-title":"Measurement"},{"key":"2544_CR60","unstructured":"S. Tripathi, A. Kumar, A. Ramesh, C. Singh, & P. Yenigalla (2019) Deep learning based emotion recognition system using speech features and transcriptions.\u00a0arXiv preprint arXiv:1906.05681"},{"key":"2544_CR61","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106547","volume":"211","author":"T Tuncer","year":"2021","unstructured":"T. Tuncer, S. Dogan, U.R. Acharya, Automated accurate speech emotion recognition system using twine shuffle pattern and iterative neighborhood component analysis techniques. Knowl. Based Syst. 211, 106547 (2021)","journal-title":"Knowl. Based Syst."},{"key":"2544_CR62","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103775","volume":"94","author":"MZ Uddin","year":"2020","unstructured":"M.Z. Uddin, E.G. Nilsson, Emotion recognition using speech and neural structured learning to facilitate edge intelligence. Eng. Appl. Artif. Intell. 94, 103775 (2020)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"2544_CR63","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/s13218-011-0107-x","volume":"25","author":"T Vogt","year":"2011","unstructured":"T. Vogt, E. Andr\u00e9, An evaluation of emotion units and feature types for real-time speech emotion recognition. KI-K\u00fcnstliche Intelligenz 25, 213\u2013223 (2011)","journal-title":"KI-K\u00fcnstliche Intelligenz"},{"issue":"5","key":"2544_CR64","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1109\/TMM.2008.927665","volume":"10","author":"Y Wang","year":"2008","unstructured":"Y. Wang, L. Guan, Recognizing human emotional state from audiovisual signals. IEEE Trans. Multimedia 10(5), 936\u2013946 (2008)","journal-title":"IEEE Trans. Multimedia"},{"issue":"13","key":"2544_CR65","first-page":"44","volume":"118","author":"P Yadav","year":"2015","unstructured":"P. Yadav, G. Aggarwal, Speech emotion classification using machine learning. Int. J. Comput. Appl. 118(13), 44 (2015)","journal-title":"Int. J. Comput. Appl."},{"issue":"1","key":"2544_CR66","first-page":"115","volume":"23","author":"Z Zhang","year":"2014","unstructured":"Z. Zhang, E. Coutinho, J. Deng, B. Schuller, Cooperative learning and its application to emotion recognition from speech. IEEE\/ACM Trans. Audio Speech Language Process. 23(1), 115\u2013126 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Language Process."},{"key":"2544_CR67","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.bspc.2018.08.035","volume":"47","author":"J Zhao","year":"2019","unstructured":"J. Zhao, X. Mao, L. Chen, Speech emotion recognition using deep 1D & 2D CNN LSTM networks. Biomed. Signal Process. Control 47, 312\u2013323 (2019)","journal-title":"Biomed. Signal Process. Control"},{"issue":"8","key":"2544_CR68","doi-asserted-by":"publisher","first-page":"11537","DOI":"10.1007\/s11042-022-12378-1","volume":"81","author":"C Zheng","year":"2022","unstructured":"C. Zheng, C. Wang, N. Jia, A two-channel speech emotion recognition model based on raw stacked waveform. Multimed. Tools Appl. 81(8), 11537\u201311562 (2022)","journal-title":"Multimed. Tools Appl."}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-023-02544-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-023-02544-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-023-02544-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T07:27:36Z","timestamp":1730791656000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-023-02544-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,6]]},"references-count":68,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["2544"],"URL":"https:\/\/doi.org\/10.1007\/s00034-023-02544-7","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,6]]},"assertion":[{"value":"8 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors affirm that they have no known financial or interpersonal Conflicts that would have appeared to have an impact on the research presented in this study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}