{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T13:37:52Z","timestamp":1781530672397,"version":"3.54.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2015,11,1]],"date-time":"2015-11-01T00:00:00Z","timestamp":1446336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Mag."],"published-print":{"date-parts":[[2015,11]]},"DOI":"10.1109\/msp.2015.2424572","type":"journal-article","created":{"date-parts":[[2015,10,14]],"date-time":"2015-10-14T19:06:25Z","timestamp":1444849585000},"page":"55-73","source":"Crossref","is-referenced-by-count":28,"title":["Expression Control in Singing Voice Synthesis: Features, approaches, evaluation, and challenges"],"prefix":"10.1109","volume":"32","author":[{"given":"Marti","family":"Umbert","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordi","family":"Bonada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masataka","family":"Goto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomoyasu","family":"Nakano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johan","family":"Sundberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"4009","article-title":"VOCALOID—Commercial singing synthesizer based on sample concatenation","author":"kenmochi","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/014892600559515"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2007.4393001"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946438"},{"key":"ref31","first-page":"343","article-title":"VocaListener: A singing-to-singing synthesis system based on iterative parameter estimation","author":"nakano","year":"0","journal-title":"Proc Sound Music Comput Conf (SMC)"},{"key":"ref30","first-page":"42","article-title":"Performance-driven control for sample-based singing voice synthesis","volume":"6","author":"janer","year":"0","journal-title":"Proc Int Conf Digital Audio Effects (DAFx)"},{"key":"ref37","author":"alonso","year":"2005","journal-title":"Expressive performance model for a singing voice synthesizer"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1115\/1.859926.paper50"},{"key":"ref35","first-page":"145","article-title":"Synthesis of singing, in Musica e Tecnologia: Industria e Cultura per lo Sviluppo del Mezzagiorno","author":"sundberg","year":"0","journal-title":"Proc Symp"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2006.01.003"},{"key":"ref28","first-page":"649","article-title":"Singing voice modelling as we know it today","volume":"90","author":"kob","year":"2004","journal-title":"Acta Acustica"},{"key":"ref27","first-page":"43","article-title":"AI and music: From composition to expressive performance","volume":"23","author":"de mantaras","year":"2002","journal-title":"AI Mag"},{"key":"ref29","author":"meron","year":"1999","journal-title":"High Quality Singing Synthesis Using the Selection-Based Synthesis Scheme"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2307\/3680822"},{"key":"ref1","first-page":"99","article-title":"Synthesis and processing of the singing voice","author":"rodet","year":"0","journal-title":"Proc 1st IEEE Benelux Workshop on Model-Based Processing and Coding of Audio (MPCA)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2271648"},{"key":"ref22","first-page":"2894","article-title":"A singing style modeling system for singing voice synthesizers","author":"saino","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-28958-5_1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/1.421129"},{"key":"ref23","author":"sundberg","year":"1987","journal-title":"The Science of the Singing Voice"},{"key":"ref26","first-page":"49","article-title":"Emulating rough and growl voice in spectral domain","author":"loscos","year":"0","journal-title":"Proc 7th Int Conf Digital Audio Effects (DAFX)"},{"key":"ref25","first-page":"1141","article-title":"An HMM-based singing voice synthesis system","author":"saino","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289140"},{"key":"ref51","year":"0","journal-title":"Music Technology Group of the Universitat Pompeu Fabra website"},{"key":"ref52","year":"0"},{"key":"ref10","first-page":"149","article-title":"Using AI and machine learning to study expressive music performance: Project survey and first report","volume":"14","author":"widmer","year":"2001","journal-title":"AI Commun"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/03057356030313003"},{"key":"ref40","author":"bonada","year":"2008","journal-title":"Voice processing and synthesis by performance sampling and spectral models"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.129.5.770"},{"key":"ref13","article-title":"Session on naturalness in synthesized speech and music","author":"ternstr\u00f6m","year":"0","journal-title":"Proc The 155th Meeting of the Acoustical Society of America (ASA)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/140154301753207458"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2478\/v10053-008-0052-x"},{"key":"ref16","author":"obin","year":"2011","journal-title":"MeLos Analysis and Modelling of Speech Prosody and Speaking Style"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84800-306-4_7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/0929821042000317804"},{"key":"ref19","author":"lesaffre","year":"2005","journal-title":"Music information retrieval conceptual framework annotation and user behaviour"},{"key":"ref4","first-page":"217","article-title":"Grand challenges in music information research","volume":"3","author":"goto","year":"2012","journal-title":"Multimodal Music Processing"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2478\/v10053-008-0051-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2007.323266"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-4123-5"},{"key":"ref8","first-page":"1","article-title":"Singing voice conversion method based on many-to-many eigenvoice conversion and training data generation using a singing-to-singing synthesis system","author":"doi","year":"0","journal-title":"APSIPA"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960481"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2012.2192811"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.825889"},{"key":"ref46","first-page":"2087","article-title":"An objective measure for estimating MOS of synthesized speech","author":"chu","year":"0","journal-title":"Proc 7th European Conf Speech Communication and Technology (Eurospeech)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2009.02.015"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2012.745579"},{"key":"ref47","first-page":"1325","article-title":"Comparison of approaches for instrumentally predicting the quality of text-to-speech systems","author":"m\u00f6ller","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref42","first-page":"211","article-title":"Recent development of the HMM-based singing voice synthesis system—Sinsy","author":"oura","year":"0","journal-title":"Proc Int Speech Communication Association (ISCA) 7th Speech Synthesis Workshop (SSW7)"},{"key":"ref41","first-page":"2347","article-title":"Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis","author":"yoshimura","year":"0","journal-title":"Proc 6th European Conf on Speech Communication and Technology"},{"key":"ref44","first-page":"213","article-title":"Systematic database creation for expressive singing voice synthesis control","author":"umbert","year":"0","journal-title":"Proc Int Speech Communication Association (ISCA) 8th Speech Synthesis Workshop (SSW8)"},{"key":"ref43","first-page":"315","article-title":"Generating singing voice expression contours based on unit selection","author":"umbert","year":"0","journal-title":"Proc Stockholm Music Acoustics Conf (SMAC 2003)"}],"container-title":["IEEE Signal Processing Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/79\/7298505\/07298564.pdf?arnumber=7298564","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:47:15Z","timestamp":1642006035000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7298564\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,11]]},"references-count":52,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/msp.2015.2424572","relation":{},"ISSN":["1053-5888"],"issn-type":[{"value":"1053-5888","type":"print"}],"subject":[],"published":{"date-parts":[[2015,11]]}}}