{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T22:19:55Z","timestamp":1767651595518,"version":"3.37.3"},"reference-count":72,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100011665","name":"Deanship of Scientific Research, King Saud University","doi-asserted-by":"publisher","award":["RG-1439-033"],"award-info":[{"award-number":["RG-1439-033"]}],"id":[{"id":"10.13039\/501100011665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Government of India\u2019s Visveswaraya Ph.D. scheme through scholarship for the first author toward completion of her Ph.D"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2923003","type":"journal-article","created":{"date-parts":[[2019,6,14]],"date-time":"2019-06-14T19:59:58Z","timestamp":1560542398000},"page":"81883-81902","source":"Crossref","is-referenced-by-count":15,"title":["Hybrid Framework for Speaker-Independent Emotion Conversion Using i-Vector PLDA and Neural Network"],"prefix":"10.1109","volume":"7","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":"ref72","doi-asserted-by":"crossref","first-page":"369","DOI":"10.21437\/Interspeech.2013-102","article-title":"Voice conversion in high-order eigen space using deep belief nets","author":"nakashika","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref70","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":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9148-2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041699"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5923\/j.ajsp.20120205.06"},{"key":"ref32","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 Transactions on Audio Speech and Language Processing"},{"key":"ref31","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":"ref30","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 Language Process"},{"key":"ref37","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":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref35","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.894527"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2015.7230458"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.925147"},{"key":"ref63","first-page":"1","article-title":"A small footprint i-vector extractor","author":"kenny","year":"2012","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66429-3_78"},{"key":"ref64","article-title":"VB calibration to improve the interface between phone recognizer and i-vector extractor","author":"br\u00fcmmer","year":"2015","journal-title":"arXiv 1510 03203"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273658"},{"key":"ref65","first-page":"1517","article-title":"A database of German emotional speech","author":"burkhardt","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03547-0_46"},{"key":"ref29","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":"ref67","first-page":"53","article-title":"Speaker-dependent audio-visual emotion recognition","author":"haq","year":"2009","journal-title":"Proc Int Conf Audio Vis Speech Process"},{"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","year":"2001","key":"ref68"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"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":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9155-3"},{"key":"ref21","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-015-0134-1"},{"key":"ref23","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-016-9386-9"},{"key":"ref25","first-page":"913","article-title":"Inter-emotion conversion using dynamic time warping and prosody imposition","author":"vekkot","year":"2016","journal-title":"Proc ISTA"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2007.347"},{"key":"ref51","first-page":"4909","article-title":"A multi-level representation of $F_{0}$ using the continuous wavelet transform and the discrete cosine transform","author":"ribeiro","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref58","first-page":"2446","article-title":"Eigenvoice conversion based on Gaussian mixture model","author":"toda","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857790"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-984"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-017-0116-2"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344665"},{"key":"ref53","first-page":"285","article-title":"Wavelets for intonation modeling in HMM speech synthesis","author":"suni","year":"2013","journal-title":"Proc ISCA Speech Synth Workshop"},{"key":"ref52","first-page":"78","article-title":"Continuous wavelet transform for analysis of speech prosody","author":"vainio","year":"2013","journal-title":"Proc TRA"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953215"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref40","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 15th Annu Conf (ISCA)"},{"key":"ref12","first-page":"879","article-title":"A study of speaker adaptation for DNN-based speech synthesis","author":"wu","year":"2015","journal-title":"Proc 16th Annu Conf (ISCA)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref14","first-page":"14","article-title":"Bayesian speaker verification with heavy-tailed priors","author":"kenny","year":"2010","journal-title":"Proc Odyssey"},{"key":"ref15","first-page":"1","article-title":"Emotion recognition using imperfect speech recognition","author":"metze","year":"2010","journal-title":"Proc of the 11th Annual ISCA"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2255278"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758146"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref19","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":"ref4","doi-asserted-by":"publisher","DOI":"10.14419\/ijet.v7i2.27.10123"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876129"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-09572-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INDICON.2016.7839028"},{"journal-title":"DIET","year":"2013","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2014.7041623"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-011-0043-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2014.17"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2013.6625307"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472664"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-9503-z"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.03.002"},{"key":"ref42","first-page":"1","article-title":"Emotional voice conversion using deep neural networks with MCC and $F_{0}$ features","author":"luo","year":"2016","journal-title":"Proc ICIS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-015-0051-3"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"1506","DOI":"10.1109\/TASLP.2014.2333242","article-title":"Exemplar-based sparse representation with residual compensation for voice conversion","volume":"22","author":"wu","year":"2014","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2014.7041640"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08736730.pdf?arnumber=8736730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T19:48:07Z","timestamp":1721418487000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8736730\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2923003","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}