{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:54:33Z","timestamp":1730199273942,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003801","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"152-159","source":"Crossref","is-referenced-by-count":3,"title":["WaveNet Factorization with Singular Value Decomposition for Voice Conversion"],"prefix":"10.1109","author":[{"given":"Hongqiang","family":"Du","sequence":"first","affiliation":[]},{"given":"Xiaohai","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref38","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Technical Report of IEICE Signal Processing Society"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1393"},{"key":"ref32","first-page":"2365","article-title":"Restructuring of deep neural network acoustic models with singular value decomposition","author":"xue","year":"2013","journal-title":"InterSpeech"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-39778-7_10"},{"key":"ref37","first-page":"1","article-title":"Phonetic posteriorgrams for many-to-one voice conversion without parallel data training","author":"sun","year":"2016","journal-title":"2016 IEEE International Conference on Multimedia and Expo (ICME)"},{"key":"ref36","article-title":"The cmu arctic speech databases","author":"kominek","year":"2004","journal-title":"Proc Fifth ISCA Speech Synthesis Workshop"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472823"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2723721"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078543"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761547"},{"journal-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","year":"2017","author":"kaneko","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"journal-title":"Efficient Neural Audio Synthesis","year":"2018","author":"kalchbrenner","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038663"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462393"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TASL.2007.907344","article-title":"Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory","volume":"15","author":"tomoki","year":"2007","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178769"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1131"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2177820"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424242"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2014.6936725"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref9","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\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1424"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref24","first-page":"1118","article-title":"Speaker-dependent wavenet vocoder","author":"tamamori","year":"2017","journal-title":"INTER-SPEECH"},{"journal-title":"WaveNet A Generative Model for Raw Audio","year":"2016","author":"van den oord","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1514"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-986"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2019,12,14]]},"location":"SG, Singapore","end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003801.pdf?arnumber=9003801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:44:17Z","timestamp":1658155457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003801","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}