{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:36:28Z","timestamp":1765546588725,"version":"3.28.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1109\/apsipaasc47483.2019.9023056","type":"proceedings-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T12:03:54Z","timestamp":1583496234000},"page":"159-164","source":"Crossref","is-referenced-by-count":8,"title":["Speaker-independent Spectral Mapping for Speech-to-Singing Conversion"],"prefix":"10.1109","author":[{"given":"Xiaoxue","family":"Gao","sequence":"first","affiliation":[]},{"given":"Xiaohai","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Rohan Kumar","family":"Das","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1537","article-title":"Transformation of prosody in voice conversion","author":"?i?man","year":"2017","journal-title":"IEEE APSIPA ASC"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/ASRU.2017.8269002"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/ICASSP.2000.861820"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/ICOT.2018.8705851"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/APSIPA.2013.6694316"},{"key":"ref30","first-page":"1836","article-title":"Combining source and system information for limited data speaker verification","author":"das","year":"2014","journal-title":"InterSpeech"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.21437\/Interspeech.2018-1131"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/PACRIM.1993.407206"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1587\/transinf.2015EDP7457"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.21437\/SSW.2016-33"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICME.2010.5582961"},{"key":"ref40","first-page":"282","article-title":"Adaptive wavenet vocoder for residual compensation in gan-based voice conversion","author":"sisman","year":"0","journal-title":"Proc IEEE\/ACL Workshop Spoken Lang Technol (SLT)"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1038\/427116a"},{"key":"ref12","first-page":"21","article-title":"The level of the singing formant and the source spectra of professional bass singers","volume":"4","author":"sundberg","year":"1970","journal-title":"Speech Transmission Lab Quart Progress Status Rep"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1007\/978-0-387-30425-0_16"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1121\/1.3518766"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/APSIPA.2016.7820901"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP.2019.8683746"},{"key":"ref17","first-page":"227","article-title":"Average modeling approach to voice conversion with non-parallel data","author":"tian","year":"0","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.23919\/APSIPA.2018.8659543"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/TASLP.2018.2878949"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/TASL.2010.2064307"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICASSP.2012.6288920"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1007\/978-1-4613-8202-7_3"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ASPAA.2007.4393001"},{"key":"ref6","first-page":"1","article-title":"Segmentation of speech signals in template-based speech to singing conversion","author":"cen","year":"2011","journal-title":"IEEE APSIPA ASC"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/TASSP.1978.1163055"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/APSIPA.2017.8282289"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.23919\/APSIPA.2018.8659615"},{"key":"ref7","first-page":"4005","article-title":"Vocal conversion from speaking voice to singing voice using straight","author":"saitou","year":"2007","journal-title":"InterSpeech"},{"key":"ref2","first-page":"2499","article-title":"A comparative study of spectral transformation techniques for singing voice synthesis","author":"lee","year":"2014","journal-title":"InterSpeech"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"2001","DOI":"10.21437\/Interspeech.2011-526","article-title":"Singing voice synthesis: Singer-dependent vibrato modeling and coherent processing of spectral envelope","author":"lee","year":"2011","journal-title":"InterSpeech"},{"key":"ref1","first-page":"2148","article-title":"I2r speech2singing perfects everyone's singing","author":"dong","year":"2014","journal-title":"InterSpeech"},{"key":"ref20","first-page":"1635","article-title":"Cross-language voice conversion based on eigenvoices","author":"charlier","year":"0","journal-title":"Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref22","first-page":"1956","article-title":"A training method of average voice model for hmm-based speech synthesis","volume":"86","author":"yamagishi","year":"2003","journal-title":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/89.876308"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1109\/ICASSP.2015.7178769"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ICASSP.2015.7178817"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1109\/TASL.2009.2038663"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/TASL.2009.2016394"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1121\/1.1975884"},{"key":"ref25","first-page":"3630","article-title":"fmllr based feature-space speaker adaptation of dnn acoustic models","author":"parthasarathi","year":"2015","journal-title":"InterSpeech"}],"event":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2019,11,18]]},"location":"Lanzhou, China","end":{"date-parts":[[2019,11,21]]}},"container-title":["2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8989870\/9023008\/09023056.pdf?arnumber=9023056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T17:51:03Z","timestamp":1666029063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9023056\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc47483.2019.9023056","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}