{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T18:48:05Z","timestamp":1785178085640,"version":"3.55.0"},"reference-count":133,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004054","name":"King Abdulaziz University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004054","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2936124","type":"journal-article","created":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T18:32:08Z","timestamp":1566498728000},"page":"117327-117345","source":"Crossref","is-referenced-by-count":612,"title":["Speech Emotion Recognition Using Deep Learning Techniques: A Review"],"prefix":"10.1109","volume":"7","author":[{"given":"Ruhul Amin","family":"Khalil","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edward","family":"Jones","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad Inayatullah","family":"Babar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tariqullah","family":"Jan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5637-4798","authenticated-orcid":false,"given":"Mohammad Haseeb","family":"Zafar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thamer","family":"Alhussain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"320","article-title":"An automatic emotion recognizer using MFCCs and hidden Markov models","author":"vyas","year":"2015","journal-title":"Proc IEEE 7th Int Congr Ultra Mod Telecommun Control Syst Workshops (ICUMT)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2279338"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.04.003"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-0327(00)00335-9"},{"key":"ref31","article-title":"Audio-visual feature selection and reduction for emotion classification","author":"haq","year":"2008","journal-title":"Proc Int Conf Auditory-Visual Speech Process (AVSP)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICIECS.2009.5362730"},{"key":"ref37","first-page":"809","article-title":"Emotion recognition in spontaneous speech using GMM","author":"neiberg","year":"2006","journal-title":"Proc Int Conf Spoken Lang Process (ICSLP)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/S1071-5819(02)00141-6"},{"key":"ref35","first-page":"1833","article-title":"Distinguishing deceptive from non-deceptive speech","author":"hirschberg","year":"2005","journal-title":"Proc 9th Eur Conf Speech Commun Technol"},{"key":"ref34","first-page":"1","article-title":"Prosody and emotions","author":"mozziconacci","year":"2002","journal-title":"Proc Speech Prosody Conf"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.7763\/JACN.2014.V2.76"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2672722"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.608022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9368-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2076804"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15184-2_6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952580"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953109"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462685"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85099-1_7"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1353"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"},{"key":"ref50","author":"jackson","year":"2014","journal-title":"SAVEE Surrey Audio-Visual Expressed Emotion (SAVEE) Database"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref58","article-title":"A breakthrough in speech emotion recognition using deep retinal convolution neural networks","author":"niu","year":"2017","journal-title":"arXiv 1707 09917"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"2362","DOI":"10.21437\/Interspeech.2010-646","article-title":"Context-sensitive multimodal emotion recognition from speech and facial expression using bidirectional LSTM modeling","author":"w\u00f6llmer","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854514"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.01.011"},{"key":"ref54","author":"wang","year":"2010","journal-title":"Machine Audition Principles Algorithms and Systems"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.03.002"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICMTMA.2010.523"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2699343.2699349"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2641480"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707732"},{"key":"ref5","first-page":"20","article-title":"Speech emotion recognition in emotional feedbackfor human-robot interaction","volume":"4","author":"r\u00e1zuri","year":"2015","journal-title":"Int J Adv Res Artificial Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICAECC.2014.7002390"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2896880"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0539018405058216"},{"key":"ref46","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":"ref45","first-page":"109","article-title":"A state of the art review on emotional speech databases","author":"ververidis","year":"2003","journal-title":"Proc 1st Richmedia Conference"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2006.145"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780195169157.001.0001","author":"coan","year":"2007","journal-title":"Handbook of Emotion Elicitation and Assessment"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5120\/431-636"},{"key":"ref41","first-page":"101","article-title":"Speech emotion recognition using support vector machine","volume":"6","author":"pan","year":"2012","journal-title":"Int J Smart Home"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-9491-z"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326051"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2116010"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-94"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/PACIIA.2008.355"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"ref73","first-page":"153","article-title":"Greedy layer-wise training of deep networks","author":"bengio","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/749604"},{"key":"ref129","article-title":"Affect-robust speech recognition by dynamic emotional adaptation","author":"schuller","year":"2006","journal-title":"Proc Speech Prosody"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref128","first-page":"i\/317","article-title":"‘Of all things the measure is man’ automatic classification of emotions and inter-labeler consistency [speech-based emotion recognition]","volume":"1","author":"steidl","year":"2005","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/1945630"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CYBER.2016.7574841"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.127"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854517"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344669"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477679"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-015-0195-2"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.90"},{"key":"ref132","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1145\/2818346.2830596","article-title":"Recurrent neural networks for emotion recognition in video","author":"kahou","year":"2015","journal-title":"Proc Int Conf Multimodal Interact"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2008.85"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2004.1329238"},{"key":"ref62","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML)"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2014.6936696"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref64","first-page":"39","article-title":"Deep belief networks for phone recognition","volume":"1","author":"mohamed","year":"2009","journal-title":"Proc NIPS Workshop Deep Learn Speech Recognit Rel Appl"},{"key":"ref65","first-page":"1537","article-title":"High-level feature representation using recurrent neural network for speech emotion recognition","author":"lee","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref66","article-title":"Emotion recognition from speech with recurrent neural networks","author":"chernykh","year":"2017","journal-title":"arXiv 1701 08071"},{"key":"ref67","first-page":"2196","article-title":"Discriminatively trained recurrent neural networks for continuous dimensional emotion recognition from audio","author":"weninger","year":"2016","journal-title":"Proc IJCAI"},{"key":"ref68","author":"kamp","year":"1990","journal-title":"Recursive Neural Networks for Associative Memory"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.008"},{"key":"ref69","first-page":"129","article-title":"Parsing natural scenes and natural language with recursive neural networks","author":"socher","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn (ICML)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2672753"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2581"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2766843"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593571"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.06.006"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1811"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.02.013"},{"key":"ref92","article-title":"Multi-modal emotion recognition on IEMOCAP dataset using deep learning","author":"tripathi","year":"2018","journal-title":"arXiv 1804 05788"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2018.08.035"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.3390\/s17071694"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref103","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":"ref102","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr.2017.0320"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953106"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953168"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1625"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref96","article-title":"Convolutional attention networks for multimodal emotion recognition from speech and text data","author":"lee","year":"2018","journal-title":"arXiv 1805 06606"},{"key":"ref97","article-title":"Adversarial auto-encoders for speech based emotion recognition","author":"sahu","year":"2018","journal-title":"arXiv 1806 02146"},{"key":"ref10","first-page":"318","article-title":"Emotion analysis in man-machine interaction systems","author":"balomenos","year":"2004","journal-title":"Proc 2nd Int Workshop Mach Learn Multimodal Interact"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"125","DOI":"10.21437\/Eurospeech.2003-80","article-title":"Emotion recognition by speech signal","author":"kwon","year":"2003","journal-title":"Proc EUROSPEECH"},{"key":"ref13","article-title":"Affective computing","author":"picard","year":"1995"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-011-9125-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363421"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2293512"},{"key":"ref82","first-page":"413","article-title":"A novel objective function to optimize neural networks for emotion recognition from speech patterns","author":"huang","year":"2010","journal-title":"Proc IEEE 2nd World Congr Nature Biolog Inspired Comput (NaBIC)"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1561\/2000000039"},{"key":"ref81","first-page":"223","article-title":"Speech emotion recognition using deep neural network and extreme learning machine","author":"han","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref84","article-title":"Feature learning in deep neural networks—Studies on speech recognition tasks","author":"yu","year":"2013","journal-title":"arXiv 1301 3605"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCS.2015.7391796"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521463"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-12568-8_13"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953138"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727297"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/UIC-ATC-ScalCom-CBDCom-IoP-SmartWorld.2016.0133"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472149"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1062"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654984"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2014.6936657"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.58"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-200"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08805181.pdf?arnumber=8805181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T12:02:27Z","timestamp":1721649747000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8805181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":133,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2936124","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}