{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T06:30:14Z","timestamp":1784615414268,"version":"3.55.0"},"reference-count":109,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100015515","name":"Kementerian Pendidikan Malaysia","doi-asserted-by":"publisher","award":["FRGS19-076-0684 (FRGS\/1\/2018\/ICT02\/UIAM\/02\/4)"],"award-info":[{"award-number":["FRGS19-076-0684 (FRGS\/1\/2018\/ICT02\/UIAM\/02\/4)"]}],"id":[{"id":"10.13039\/501100015515","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3068045","type":"journal-article","created":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T20:22:09Z","timestamp":1616444529000},"page":"47795-47814","source":"Crossref","is-referenced-by-count":333,"title":["A Comprehensive Review of Speech Emotion Recognition Systems"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2335-0420","authenticated-orcid":false,"given":"Taiba Majid","family":"Wani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3345-4669","authenticated-orcid":false,"given":"Teddy Surya","family":"Gunawan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2060-1407","authenticated-orcid":false,"given":"Syed Asif Ahmad","family":"Qadri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3686-3575","authenticated-orcid":false,"given":"Mira","family":"Kartiwi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4673-6534","authenticated-orcid":false,"given":"Eliathamby","family":"Ambikairajah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-6626-9_22"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10237-014-0632-2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISMSIT.2018.8567303"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-017-9407-3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1515\/jaiscr-2016-0018"},{"key":"ref30","first-page":"1099","article-title":"Fear-type emotions of the SAFE corpus: Annotation issues","author":"clavel","year":"2006","journal-title":"Proc 5th Int Conf Lang Resour Eval (LREC)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70772-3_1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2015.119"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967306"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-77592-0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2008.4766487"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5829\/idosi.ije.2014.27.01a.11"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1109\/TASL.2006.876113","article-title":"Prosody conversion from neutral speech to emotional speech","volume":"14","author":"tao","year":"2006","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2006.145"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.20"},{"key":"ref24","first-page":"1","article-title":"Releasing a thoroughly annotated and processed spontaneous emotional database: The FAU Aibo emotion corpus","author":"batliner","year":"2008","journal-title":"Proc Workshop Corpora Res Emotion Affect LREC"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref101","first-page":"162","article-title":"Automatic emotion recognition from speech using artificial neural networks with gender-dependent databases","author":"firoz","year":"2009","journal-title":"Proc Int Conf Adv Comput Control Telecommun Technol"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9172-2"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC47524.2020.9031207"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2553038"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683172"},{"key":"ref51","first-page":"1619","article-title":"Detection of stress and emotion in speech using traditional and FFT based log energy features","author":"new","year":"2003","journal-title":"Proc 4th Int Conf Inf Technol"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-817736-5.00009-0"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.143"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPCT.2017.8074220"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18178\/ijmlc.2018.8.3.687"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21402-8_35"},{"key":"ref54","first-page":"101","article-title":"Speech emotion recognition using support vector machine","volume":"6","author":"pan","year":"2012","journal-title":"Smart Home"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178872"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(03)00099-2"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CONFLUENCE.2016.7508170"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.heares.2014.10.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2641480"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0197160"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-016-0412-1"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.proeng.2012.06.394"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.12.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936124"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.5539\/mas.v13n11p31"},{"key":"ref45","article-title":"Machine learning classifiers","author":"asiri","year":"2018","journal-title":"Towards Data Science"},{"key":"ref48","first-page":"1","article-title":"Emotion recognition in spontaneous speech using GMMs","author":"neiberg","year":"2006","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref47","first-page":"47","article-title":"Emotion recognition from speech with Gaussian mixture models & via boosted GMM","volume":"3","author":"patel","year":"2017","journal-title":"Int J Eng Sci Res"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-2037-8_10"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2019.01.027"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/89.905995"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319457"},{"key":"ref73","first-page":"2363","article-title":"Emotion recognition on the basis of audio signal using Naïve Bayes classifier","author":"bhakre","year":"2016","journal-title":"Proc Int Conf Adv Comput Commun Inform"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.04.226"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"ref70","article-title":"Essentials of deep learning?: Introduction to long short term memory","author":"pranjal","year":"2017","journal-title":"Anal Vidhya"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-015-9275-7"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.5120\/ijca2016910710"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.06.004"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.58"},{"key":"ref78","first-page":"1","article-title":"Speech emotion recognition using convolutional and Recurrent Neural Networks","author":"lim","year":"2017","journal-title":"Proc Asia–Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref79","first-page":"137","article-title":"Speech emotion recognition with deep learning","author":"har\u00e1r","year":"2017","journal-title":"Proc 4th Int Conf Signal Process Integr Netw"},{"key":"ref60","first-page":"1017","article-title":"Emotion recognition using prosodic and spectral features of speech and Naïve Bayes classifier","author":"khan","year":"2018","journal-title":"Proc Int Conf Wireless Commun Signal Process Netw (WiSPNET)"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ITA.2017.8023477"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.11591\/ijeecs.v10.i2.pp554-561"},{"key":"ref63","article-title":"On the origin of deep learning","author":"wang","year":"2017","journal-title":"arXiv 1702 07800"},{"key":"ref64","first-page":"268","article-title":"Learning deep sigmoid belief networks with data augmentation","author":"gan","year":"2015","journal-title":"Proc Artif Intell Statist"},{"key":"ref65","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1002\/spe.2487","article-title":"Deep learning and SVM-based emotion recognition from Chinese speech for smart affective services","volume":"47","author":"zhang","year":"2017","journal-title":"Softw Pract Exper"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3390\/s17071694"},{"key":"ref67","article-title":"A gentle introduction to exploding gradients in neural networks","author":"brownlee","year":"2017","journal-title":"Machine Learning Mastery"},{"key":"ref68","first-page":"1","article-title":"High-level feature representation using recurrent neural network for speech emotion recognition","author":"lee","year":"2015","journal-title":"Proc 16th Annu Conf Int Speech Commun Assoc"},{"key":"ref2","first-page":"1","article-title":"Automatic speech based emotion recognition using paralinguistics features","volume":"67","author":"hook","year":"2019","journal-title":"Bull Polish Acad Sci Tech Sci"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-802398-3.00002-7"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT.2017.8204149"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.03.005"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462219"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.5772\/intechopen.84856"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1080\/019697201750361283"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSEC49089.2020.9215376"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.3390\/a10020070"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCUBEA47591.2019.9129067"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2014.6973926"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3252"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1080\/019697201750361283"},{"key":"ref90","first-page":"112","article-title":"Multimodal speech emotion recognition using audio and text","author":"yoon","year":"2019","journal-title":"Proc IEEE Spoken Lang Technol Workshop"},{"key":"ref103","article-title":"A CNN-assisted enhanced audio signal processing for speech emotion recognition","author":"mustaqeem","year":"2020","journal-title":"SENSORS"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1811"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-020-01538-x"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-020-01486-8"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2990405"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICWT50448.2020.9243622"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-3003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.06.016"},{"key":"ref13","first-page":"1312","article-title":"A critical insight into multi-languages speech emotion databases","volume":"8","author":"qadri","year":"2019","journal-title":"Bull Electr Eng Inform"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-9491-z"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.01.003"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICICCT.2017.7975169"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461431"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23851\/mjs.v28i3.48"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-017-9396-2"},{"key":"ref18","first-page":"1","article-title":"A database of German emotional speech","author":"burkhardt","year":"2005","journal-title":"Proc 9th Eur Conf Speech Commun Technol"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.005"},{"key":"ref19","author":"jackson","year":"2014","journal-title":"Surrey audio-visual expressed emotion (savee) database"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.5220\/0006611601750182"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/1945630"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.10.004"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICNIDC.2018.8525706"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682541"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-018-0145-5"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.10.009"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09383000.pdf?arnumber=9383000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:22:15Z","timestamp":1698085335000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383000\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":109,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3068045","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}