{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T18:51:06Z","timestamp":1774551066602,"version":"3.50.1"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2988781","type":"journal-article","created":{"date-parts":[[2020,4,21]],"date-time":"2020-04-21T00:14:58Z","timestamp":1587428098000},"page":"74627-74647","source":"Crossref","is-referenced-by-count":21,"title":["Emotional Voice Conversion Using a Hybrid Framework With Speaker-Adaptive DNN and Particle-Swarm-Optimized Neural Network"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6638-214X","authenticated-orcid":false,"given":"Susmitha","family":"Vekkot","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1041-5125","authenticated-orcid":false,"given":"Deepa","family":"Gupta","sequence":"additional","affiliation":[]},{"given":"Mohammed","family":"Zakariah","sequence":"additional","affiliation":[]},{"given":"Yousef Ajami","family":"Alotaibi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-007-0002-0"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/MHS.1995.494215"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2008.2008606"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC.2007.627"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03547-0_46"},{"key":"ref77","first-page":"53","article-title":"Speaker-dependent audio-visual emotion recognition","author":"haq","year":"2009","journal-title":"Proc Int Conf Audio Visual Speech Process"},{"key":"ref74","first-page":"760","article-title":"Particle swarm optimization","author":"kennedy","year":"2010","journal-title":"Encyclopedia of Machine Learning"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.03.002"},{"key":"ref75","first-page":"1517","article-title":"A database of German emotional speech","author":"burkhardt","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref38","article-title":"Emotional end-to-end neural speech synthesizer","author":"lee","year":"2017","journal-title":"arXiv 1711 05447"},{"key":"ref78","first-page":"2787","article-title":"Instantaneous pitch estimation based on RAPT framework","author":"azarov","year":"2012","journal-title":"Proc Eur Signal Process Conf (EUSIPCO)"},{"key":"ref79","year":"2001","journal-title":"Perceptual evaluation of speech quality PESQ an objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-015-0051-3"},{"key":"ref32","first-page":"1969","article-title":"Deep neural network based trainable voice source model for synthesis of speech with varying vocal effort","author":"raitio","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9148-2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041699"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472664"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2013.6625307"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2895923"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIS.2016.7550889"},{"key":"ref60","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":"ref62","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":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639346"},{"key":"ref63","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"669","DOI":"10.21437\/Interspeech.2011-272","article-title":"Voice conversion using GMM with enhanced global variance","author":"benisty","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2010.08.002"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/NCC.2019.8732259"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970104"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2019.8929432"},{"key":"ref67","first-page":"527","article-title":"A nonlinear squeezing of the continuous wavelet transform based on auditory nerve models","author":"daubechies","year":"1996","journal-title":"Wavelets in Medicine and Biology"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.3390\/en11061525"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1995.488968"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAPR.2015.7050705"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IC3.2014.6897219"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"2401","DOI":"10.21437\/Eurospeech.2003-661","article-title":"GMM-based voice conversion applied to emotional speech synthesis","author":"kawanami","year":"2003","journal-title":"Proc 8th Eur Conf Speech Commun Technol"},{"key":"ref22","first-page":"490","article-title":"A system for transforming the emotion in speech: Combining data-driven conversion techniques for prosody and voice quality","author":"inanoglu","year":"2007","journal-title":"Proc ISCA"},{"key":"ref21","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":"ref24","doi-asserted-by":"publisher","DOI":"10.5923\/j.ajsp.20120205.06"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1394","DOI":"10.1109\/TASL.2009.2034771","article-title":"Hierarchical prosody conversion using regression-based clustering for emotional speech synthesis","volume":"18","author":"wu","year":"2010","journal-title":"IEEE Trans Audio Speech Language Process"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"928","DOI":"10.1007\/s12559-014-9283-y","article-title":"GMM-based evaluation of emotional style transformation in Czech and Slovak","volume":"6","author":"p?ibil","year":"2014","journal-title":"Cognit Comput"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-984"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.03.008"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-7012(00)00201-3"},{"key":"ref58","author":"yegnanarayana","year":"2009","journal-title":"Artificial Neural Networks"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2019.3"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683865"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2923003"},{"key":"ref54","article-title":"Nonparallel emotional speech conversion","author":"gao","year":"2018","journal-title":"arXiv 1811 01174"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820690"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659599"},{"key":"ref10","first-page":"1","article-title":"The generation of affect in synthesized speech","volume":"8","author":"cahn","year":"1990","journal-title":"J American Voice I\/O Society"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-9503-z"},{"key":"ref12","first-page":"1798","article-title":"Emovoice: A system to generate emotions in speech","author":"cabral","year":"2006","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9155-3"},{"key":"ref14","first-page":"462","article-title":"Significance of glottal closure instants detection algorithms in vocal emotion conversion","author":"vekkot","year":"2016","journal-title":"Proc 4th Int Workshop Soft Comput Appl (SOFA)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-015-0134-1"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518785"},{"key":"ref16","first-page":"913","article-title":"Inter-emotion conversion using dynamic time warping and prosody imposition","author":"vekkot","year":"2016","journal-title":"Proc ISTA"},{"key":"ref81","first-page":"755","article-title":"Perceptual evaluation of speech quality (PESQ) the new ITU standard for end-to-end speech quality assessment Part I—Time-delay compensation","volume":"50","author":"rix","year":"2002","journal-title":"J Audio Eng Soc"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-016-9386-9"},{"key":"ref84","doi-asserted-by":"crossref","first-page":"2969","DOI":"10.21437\/Interspeech.2011-743","article-title":"Neutral to target emotion conversion using source and suprasegmental information","author":"govind","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273658"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2350"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66429-3_78"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-09572-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876129"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-169926"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INDICON.2016.7839028"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9180-2"},{"key":"ref8","year":"2013","journal-title":"Technology Development for Indian Languages Programme"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.06.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2014.7041623"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-017-0116-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2014.17"},{"key":"ref46","first-page":"78","article-title":"Continuous wavelet transform for analysis of speech prosody","author":"vainio","year":"2013","journal-title":"Proc TRA"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178904"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344665"},{"key":"ref47","first-page":"78","article-title":"Wavelets for intonation modeling in HMM speech synthesis","author":"suni","year":"2013","journal-title":"Proc ISCA Speech Synth Workshop"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-019-09626-5"},{"key":"ref41","first-page":"334","article-title":"Significance of epoch identification accuracy in prosody modification for effective emotion conversion","author":"priya","year":"2018","journal-title":"Proc Int Symp Signal Process Intell Recognit Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2007.347"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-011-0043-3"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09072171.pdf?arnumber=9072171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T21:30:42Z","timestamp":1666387842000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9072171\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2988781","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}