{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T14:10:38Z","timestamp":1790691038283,"version":"4.1.0"},"reference-count":60,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","jvoice.org","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Voice"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.jvoice.2026.09.013","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T13:52:18Z","timestamp":1790689938000},"update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["Speech Emotion Recognition Using Hybrid VMD and EWT Based Cepstral Feature Extraction"],"prefix":"10.1016","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8076-8295","authenticated-orcid":false,"given":"Siba Prasad","family":"Mishra","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pankaj","family":"Warule","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sudhansu Sekhar","family":"Nayak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"B.Kameswara","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suman","family":"Deb","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvoice.2026.09.013_bib1","doi-asserted-by":"crossref","DOI":"10.1016\/j.specom.2023.102986","article-title":"Chirplet transform based time frequency analysis of speech signal for automated speech emotion recognition","volume":"155","author":"Mishra","year":"2023","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2026.09.013_bib2","article-title":"A survey of speech emotion recognition in natural environment","volume":"110","author":"Fahad","year":"2021","journal-title":"Digit Signal Process"},{"key":"10.1016\/j.jvoice.2026.09.013_bib3","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1109\/TCYB.2017.2787717","article-title":"Multiscale amplitude feature and significance of enhanced vocal tract information for emotion classification","volume":"49","author":"Deb","year":"2018","journal-title":"IEEE Trans Cybern"},{"key":"10.1016\/j.jvoice.2026.09.013_bib4","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/TSA.2004.838534","article-title":"Toward detecting emotions in spoken dialogs","volume":"13","author":"Lee","year":"2005","journal-title":"IEEE Trans Speech Audio Process"},{"key":"10.1016\/j.jvoice.2026.09.013_bib5","doi-asserted-by":"crossref","unstructured":"B. Pragati C. Kolli D. Jain A. Sunethra N. Nagarathna Evaluation of Customer Care Executives Using Speech Emotion Recognition Machine Learning, Image Processing, Network Security and Data Sciences: Select Proceedings of 3rd International Conference on MIND 2021 2023 Springer, 187 198.","DOI":"10.1007\/978-981-19-5868-7_14"},{"key":"10.1016\/j.jvoice.2026.09.013_bib6","first-page":"3217","article-title":"Mental illness disorder diagnosis using emotion variation detection from continuous English speech","author":"Lalitha","year":"2021","journal-title":"Comput Mater Contin"},{"key":"10.1016\/j.jvoice.2026.09.013_bib7","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1109\/TBME.2010.2091640","article-title":"Detection of clinical depression in adolescents\u2019 speech during family interactions","volume":"58","author":"Low","year":"2010","journal-title":"IEEE Trans Biomed Eng"},{"key":"10.1016\/j.jvoice.2026.09.013_bib8","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2022.108637","article-title":"Shoelace pattern-based speech emotion recognition of the lecturers in distance education: Shoepat23","volume":"190","author":"Tanko","year":"2022","journal-title":"Appl Acoust"},{"key":"10.1016\/j.jvoice.2026.09.013_bib9","doi-asserted-by":"crossref","unstructured":"J. Frommel C. Schrader M. Weber Towards emotion-based adaptive games: Emotion recognition via input and performance features Proceedings of the 2018 Annual Symposium on Computer-Human Interaction in Play 2018 173 185.","DOI":"10.1145\/3242671.3242672"},{"key":"10.1016\/j.jvoice.2026.09.013_bib10","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1109\/TITS.2010.2092770","article-title":"Driver inattention monitoring system for intelligent vehicles: a review","volume":"12","author":"Dong","year":"2010","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"10.1016\/j.jvoice.2026.09.013_bib11","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2020.101894","article-title":"Speech emotion recognition with deep convolutional neural networks","volume":"59","author":"Issa","year":"2020","journal-title":"Biomed Signal Process Control"},{"key":"10.1016\/j.jvoice.2026.09.013_bib12","article-title":"Improvement of emotion classification performance using multi-resolution variational mode decomposition method, biomedical","volume":"89","author":"Mishra","year":"2024","journal-title":"Signal Process Control"},{"key":"10.1016\/j.jvoice.2026.09.013_bib13","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2023.109578","article-title":"Variational mode decomposition based acoustic and entropy features for speech emotion recognition","volume":"212","author":"Mishra","year":"2023","journal-title":"Appl Acoust"},{"key":"10.1016\/j.jvoice.2026.09.013_bib14","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1016\/j.apacoust.2018.11.028","article-title":"A novel feature selection method for speech emotion recognition","volume":"146","author":"\u00d6zseven","year":"2019","journal-title":"Appl Acoust"},{"key":"10.1016\/j.jvoice.2026.09.013_bib15","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2021.108046","article-title":"Improved speech emotion recognition with mel frequency magnitude coefficient","volume":"179","author":"Ancilin","year":"2021","journal-title":"Appl Acoust"},{"key":"10.1016\/j.jvoice.2026.09.013_bib16","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2024.110403","article-title":"Speech emotion recognition using multi resolution hilbert transform based spectral and entropy features","volume":"229","author":"Mishra","year":"2025","journal-title":"Appl Acoust"},{"key":"10.1016\/j.jvoice.2026.09.013_bib17","doi-asserted-by":"crossref","unstructured":"S.K. Pandey H.S. Shekhawat S.M. Prasanna Deep learning techniques for speech emotion recognition: A review 2019 29th International Conference Radioelektronika (RADIOELEKTRONIKA) 2019 IEEE, 1 6.","DOI":"10.1109\/RADIOELEK.2019.8733432"},{"key":"10.1016\/j.jvoice.2026.09.013_bib18","doi-asserted-by":"crossref","first-page":"36018","DOI":"10.1109\/ACCESS.2022.3163856","article-title":"Hybrid lstm-transformer model for emotion recognition from speech audio files","volume":"10","author":"Andayani","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2026.09.013_bib19","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2020.103939","article-title":"Detection of shockable ventricular cardiac arrhythmias from ecg signals using ffrewt filter-bank and deep convolutional neural network","volume":"124","author":"Panda","year":"2020","journal-title":"Comput Biol Med"},{"key":"10.1016\/j.jvoice.2026.09.013_bib20","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1109\/LSP.2014.2311435","article-title":"Time-frequency feature and ams-gmm mask for acoustic emotion classification","volume":"21","author":"Z\u00e3o","year":"2014","journal-title":"IEEE Signal Process Lett"},{"key":"10.1016\/j.jvoice.2026.09.013_bib21","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1109\/89.848224","article-title":"A comparative study of traditional and newly proposed features for recognition of speech under stress","volume":"8","author":"Bou-Ghazale","year":"2002","journal-title":"IEEE Trans Speech Audio Process"},{"key":"10.1016\/j.jvoice.2026.09.013_bib22","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1109\/TSP.2013.2288675","article-title":"Variational mode decomposition","volume":"62","author":"Dragomiretskiy","year":"2013","journal-title":"IEEE Trans Signal Process"},{"key":"10.1016\/j.jvoice.2026.09.013_bib23","doi-asserted-by":"crossref","first-page":"3999","DOI":"10.1109\/TSP.2013.2265222","article-title":"Empirical wavelet transform","volume":"61","author":"Gilles","year":"2013","journal-title":"IEEE Trans Signal Process"},{"key":"10.1016\/j.jvoice.2026.09.013_bib24","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1109\/MSP.2017.2672759","article-title":"Effectively interpreting discrete wavelet transformed signals [lecture notes]","volume":"34","author":"Guido","year":"2017","journal-title":"IEEE Signal Process Mag"},{"key":"10.1016\/j.jvoice.2026.09.013_bib25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.physrep.2022.08.001","article-title":"Wavelets behind the scenes: Practical aspects, insights, and perspectives","volume":"985","author":"Guido","year":"2022","journal-title":"Phys Rep"},{"key":"10.1016\/j.jvoice.2026.09.013_bib26","article-title":"Speech emotion recognition using energy based adaptive mode selection","volume":"171","author":"Taran","year":"2025","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2026.09.013_bib27","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-025-95734-z","article-title":"Speech emotion recognition with light weight deep neural ensemble model using hand crafted features","volume":"15","author":"Chowdhury","year":"2025","journal-title":"Sci Rep"},{"key":"10.1016\/j.jvoice.2026.09.013_bib28","doi-asserted-by":"crossref","unstructured":"D.H. Rudd X. Gao M.R. Islam H. Huo G. Xu Speech emotion recognition using mel spectrogram hpca and variational mode decomposition 2024 11th International Conference on Behavioural and Social Computing (BESC) 2024 IEEE, 1 7.","DOI":"10.1109\/BESC64747.2024.10780726"},{"key":"10.1016\/j.jvoice.2026.09.013_bib29","doi-asserted-by":"crossref","unstructured":"Z. Wang J. Yan Y. Wang X. Wang Speech emotion feature extraction method based on improved mfcc and imfcc fusion features 2023 IEEE 2nd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA) 2023 IEEE, 1917 1924.","DOI":"10.1109\/EEBDA56825.2023.10090810"},{"key":"10.1016\/j.jvoice.2026.09.013_bib30","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1007\/s10772-022-09970-z","article-title":"Emotional speech analysis and classification using variational mode decomposition","volume":"25","author":"Dendukuri","year":"2022","journal-title":"Int J Speech Technol"},{"key":"10.1016\/j.jvoice.2026.09.013_bib31","article-title":"A nonlinear feature extraction approach for speech emotion recognition using vmd and tkeo","volume":"214","author":"Taran","year":"2023","journal-title":"Appl Acoust"},{"key":"10.1016\/j.jvoice.2026.09.013_bib32","doi-asserted-by":"crossref","DOI":"10.1016\/j.specom.2024.103148","article-title":"Fixed frequency range empirical wavelet transform based acoustic and entropy features for speech emotion recognition","volume":"166","author":"Mishra","year":"2025","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2026.09.013_bib33","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101847","article-title":"Emotion recognition from unimodal to multimodal analysis: a review","author":"Ezzameli","year":"2023","journal-title":"Inf Fusion"},{"key":"10.1016\/j.jvoice.2026.09.013_bib34","doi-asserted-by":"crossref","DOI":"10.1007\/s11227-026-08672-6","article-title":"Emotion classification from speech using empirical wavelet transform derived spectral and entropy features with dnn classifier: Dp pattnaik and bssid vemuri","volume":"82","author":"Pattnaik","year":"2026","journal-title":"J Supercomput"},{"key":"10.1016\/j.jvoice.2026.09.013_bib35","series-title":"Artificial Intelligence: A Tool for Effective Diagnostics","article-title":"Nikhil, Speech emotion recognition using empirical wavelet transform and cubic support vector machine","author":"Hosain","year":"2024"},{"key":"10.1016\/j.jvoice.2026.09.013_bib36","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.specom.2019.09.002","article-title":"Automatic speech emotion recognition using an optimal combination of features based on emd-tkeo","volume":"114","author":"Kerkeni","year":"2019","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2026.09.013_bib37","doi-asserted-by":"crossref","unstructured":"D. Hason Rudd H. Huo G. Xu An extended variational mode decomposition algorithm developed speech emotion recognition performance Pacific-Asia Conference on Knowledge Discovery and Data Mining 2023 Springer 219 231.","DOI":"10.1007\/978-3-031-33380-4_17"},{"key":"10.1016\/j.jvoice.2026.09.013_bib38","article-title":"Speech emotion recognition using ramanujan fourier transform","volume":"201","author":"Flower","year":"2022","journal-title":"Appl Acoust"},{"key":"10.1016\/j.jvoice.2026.09.013_bib39","doi-asserted-by":"crossref","first-page":"1919","DOI":"10.1007\/s40747-021-00295-z","article-title":"Emotion classification from speech signal based on empirical mode decomposition and non-linear features: speech emotion recognition","volume":"7","author":"Krishnan","year":"2021","journal-title":"Complex Intell Syst"},{"key":"10.1016\/j.jvoice.2026.09.013_bib40","first-page":"521","article-title":"Adaptive compensation algorithm in open vocabulary mandarin speaker-independent speech recognition","volume":"7","author":"Al-dulaimy","year":"2002","journal-title":"Tsinghua Sci Technol"},{"key":"10.1016\/j.jvoice.2026.09.013_bib41","volume":"155","author":"Ince","year":"2013"},{"key":"10.1016\/j.jvoice.2026.09.013_bib42","doi-asserted-by":"crossref","first-page":"2679","DOI":"10.1016\/j.jfranklin.2015.04.001","article-title":"Instantaneous voiced\/non-voiced detection in speech signals based on variational mode decomposition","volume":"352","author":"Upadhyay","year":"2015","journal-title":"J Frankl Inst"},{"key":"10.1016\/j.jvoice.2026.09.013_bib43","doi-asserted-by":"crossref","unstructured":"S. Lahmiri M. Boukadoum Physiological signal denoising with variational mode decomposition and weighted reconstruction after dwt thresholding 2015 IEEE international symposium on circuits and systems (ISCAS) 2015 IEEE, 806 809.","DOI":"10.1109\/ISCAS.2015.7168756"},{"key":"10.1016\/j.jvoice.2026.09.013_bib44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10916-016-0441-5","article-title":"Detection of shockable ventricular arrhythmia using variational mode decomposition","volume":"40","author":"Tripathy","year":"2016","journal-title":"J Med Syst"},{"key":"10.1016\/j.jvoice.2026.09.013_bib45","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.epsr.2018.10.014","article-title":"Identification of electromechanical oscillatory modes based on variational mode decomposition","volume":"167","author":"Paternina","year":"2019","journal-title":"Electr Power Syst Res"},{"key":"10.1016\/j.jvoice.2026.09.013_bib46","doi-asserted-by":"crossref","unstructured":"B. Karan K. Mahto S.S. Sahu Detection of parkinson disease using variational mode decomposition of speech signal 2018 International Conference on Communication and Signal Processing (ICCSP) 2018 IEEE, 0508 0512.","DOI":"10.1109\/ICCSP.2018.8524445"},{"key":"10.1016\/j.jvoice.2026.09.013_bib47","series-title":"Computer Science and Applied Mathematics","article-title":"Constrained optimization and lagrange multiplier methods, comput","author":"Bertsekas","year":"1982"},{"key":"10.1016\/j.jvoice.2026.09.013_bib48","doi-asserted-by":"crossref","DOI":"10.1049\/el:19991095","article-title":"Comparison of discrete wavelet and fourier transforms for ecg beat classification","volume":"35","author":"Dokur","year":"1999","journal-title":"Electron Lett"},{"key":"10.1016\/j.jvoice.2026.09.013_bib49","doi-asserted-by":"crossref","first-page":"4509","DOI":"10.1109\/JSEN.2019.2896308","article-title":"A novel approach for detection of myocardial infarction from ecg signals of multiple electrodes","volume":"19","author":"Tripathy","year":"2019","journal-title":"IEEE Sens J"},{"key":"10.1016\/j.jvoice.2026.09.013_bib50","first-page":"7335","article-title":"Voice command recognition system based on mfcc and dtw","volume":"2","author":"Bala","year":"2010","journal-title":"Int J Eng Sci Technol"},{"key":"10.1016\/j.jvoice.2026.09.013_bib51","doi-asserted-by":"crossref","first-page":"3155","DOI":"10.1007\/s11760-023-02537-8","article-title":"Machine learning approach for detecting covid-19 from speech signal using mel frequency magnitude coefficient","author":"Nayak","year":"2023","journal-title":"Signal Image Video Process"},{"key":"10.1016\/j.jvoice.2026.09.013_bib52","doi-asserted-by":"crossref","first-page":"2157","DOI":"10.1016\/j.eswa.2011.07.065","article-title":"Classification of speech dysfluencies with mfcc and lpcc features","volume":"39","author":"Ai","year":"2012","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.jvoice.2026.09.013_bib53","doi-asserted-by":"crossref","unstructured":"S. Latif, R. Rana, S. Younis, J. Qadir, J. Epps, Transfer learning for improving speech emotion classification accuracy, arXiv preprint arXiv:1801.06353 (2018).","DOI":"10.21437\/Interspeech.2018-1625"},{"key":"10.1016\/j.jvoice.2026.09.013_bib54","doi-asserted-by":"crossref","unstructured":"M.H. Pham F.M. Noori J. Torresen Emotion recognition using speech data with convolutional neural network 2021 IEEE 2nd International Conference on Signal, Control and Communication (SCC) 2021 IEEE, 182 187.","DOI":"10.1109\/SCC53769.2021.9768372"},{"key":"10.1016\/j.jvoice.2026.09.013_bib55","doi-asserted-by":"crossref","first-page":"15","DOI":"10.3991\/ijoe.v16i04.11870","article-title":"Speaker awareness for speech emotion recognition","volume":"16","author":"Assun\u00e7\u00e3o","year":"2020","journal-title":"Int J Online Biomed Eng"},{"key":"10.1016\/j.jvoice.2026.09.013_bib56","first-page":"1","article-title":"Speech emotion recognition using mfcc-based entropy feature, Signal","author":"Mishra","year":"2023","journal-title":"Image Video Process"},{"key":"10.1016\/j.jvoice.2026.09.013_bib57","doi-asserted-by":"crossref","unstructured":"N. Scheidwasser-Clow M. Kegler P. Beckmann M. Cernak Serab: A multi-lingual benchmark for speech emotion recognition Serab: A multi-lingual benchmark for speech emotion recognition, In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022 IEEE, 7697 7701.","DOI":"10.1109\/ICASSP43922.2022.9747348"},{"key":"10.1016\/j.jvoice.2026.09.013_bib58","doi-asserted-by":"crossref","first-page":"190784","DOI":"10.1109\/ACCESS.2020.3031763","article-title":"A speech emotion recognition model based on multi-level local binary and local ternary patterns","volume":"8","author":"S\u00f6nmez","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2026.09.013_bib59","first-page":"1","article-title":"A statistical feature extraction for deep speech emotion recognition in a bilingual scenario","author":"Sekkate","year":"2022","journal-title":"Multimed Tools Appl"},{"key":"10.1016\/j.jvoice.2026.09.013_bib60","doi-asserted-by":"crossref","unstructured":"M.A. Jalal E. Loweimi R.K. Moore T. Hain Learning temporal clusters using capsule routing for speech emotion recognition Proceedings of interspeech 2019, ISCA 2019 1701 1705.","DOI":"10.21437\/Interspeech.2019-3068"}],"container-title":["Journal of Voice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199726004881?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199726004881?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T13:52:29Z","timestamp":1790689949000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0892199726004881"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":60,"alternative-id":["S0892199726004881"],"URL":"https:\/\/doi.org\/10.1016\/j.jvoice.2026.09.013","relation":{},"ISSN":["0892-1997"],"issn-type":[{"value":"0892-1997","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Speech Emotion Recognition Using Hybrid VMD and EWT Based Cepstral Feature Extraction","name":"articletitle","label":"Article Title"},{"value":"Journal of Voice","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvoice.2026.09.013","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Voice Foundation. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}