{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T04:33:04Z","timestamp":1754109184616,"version":"3.28.0"},"reference-count":41,"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\/asru46091.2019.9004008","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"200-207","source":"Crossref","is-referenced-by-count":12,"title":["Bootstrapping Non-Parallel Voice Conversion from Speaker-Adaptive Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Hieu-Thi","family":"Luong","sequence":"first","affiliation":[]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-29"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"195","DOI":"10.21437\/Odyssey.2018-28","article-title":"The voice conversion challenge 2018: Promoting development of parallel and nonparallel methods","author":"lorenzo-trueba","year":"2018","journal-title":"Proc Odyssey"},{"journal-title":"Unsu-pervised end-to-end learning of discrete linguistic units for voice conversion","year":"2019","author":"liu","key":"ref33"},{"journal-title":"Combining adversarial training and disentangled speech representation for robust zero-resource subword modeling","year":"2019","author":"feng","key":"ref32"},{"journal-title":"The zero resource speech challenge 2019 TTS without T","year":"2019","author":"dunbar","key":"ref31"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"528","DOI":"10.21437\/Interspeech.2009-192","article-title":"State mapping based method for cross-lingual speaker adaptation in hmm-based speech synthesis","author":"wu","year":"2009","journal-title":"Proc INTERSPEECH"},{"journal-title":"CSTR VCTK corpus English multispeaker corpus for CSTR voice cloning toolkit","year":"2017","author":"veaux","key":"ref37"},{"key":"ref36","first-page":"2594","article-title":"Au-tomatic discovery of a phonetic inventory for unwritten languages for statistical speech synthesis","author":"muthukumar","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639221"},{"journal-title":"Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks","year":"2019","author":"eloff","key":"ref34"},{"key":"ref10","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":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-247"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"journal-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","year":"2017","author":"kaneko","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462342"},{"journal-title":"Vqvae unsupervised unit discovery and multi-scale code2spec inverter for zerospeech challenge 2019","year":"2019","author":"tjandra","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639647"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"journal-title":"Non-parallel sequence-to-sequence voice conversion with disentangled linguistic and speaker representations","year":"2019","author":"jing-xuan","key":"ref18"},{"journal-title":"A unified speaker adaptation method for speech synthesis using transcribed and untranscribed speech with backpropagation","year":"2019","author":"luong","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683746"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1587\/transfun.E96.A.1946"},{"key":"ref27","first-page":"361","article-title":"Evaluation of cross-language voice conversion based on GMM and Straight","author":"mashimo","year":"2001","journal-title":"Proc EU-ROSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1250\/ast.11.71"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038669"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852225"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref8","first-page":"2254","article-title":"Map-based adaptation for speech conversion using adaptation data selection and non-parallel training","author":"lee","year":"2006","journal-title":"Proc Inter-speech"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"2413","DOI":"10.21437\/Eurospeech.2003-664","article-title":"Voice conversion with smoothed gmm and map adaptation","author":"chen","year":"2003","journal-title":"Proc EUROSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"key":"ref9","first-page":"2446","article-title":"Eigenvoice conversion based on gaussian mixture model","author":"toda","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref1","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 Trans Audio Speech Language Process"},{"journal-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","year":"2018","author":"ye","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"journal-title":"Fitting new speakers based on a short untranscribed sample","year":"2018","author":"nachmani","key":"ref21"},{"journal-title":"Joint training framework for text-to-speech and voice conversion using multi-source tacotron and wavenet","year":"2019","author":"zhang","key":"ref24"},{"journal-title":"End-to-end text-to-speech for low-resource languages by cross-lingual transfer learning","year":"2019","author":"tu","key":"ref41"},{"journal-title":"Acvae-vc Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder","year":"2018","author":"kameoka","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1121\/1.402284"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1043"}],"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\/09004008.pdf?arnumber=9004008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T08:49:47Z","timestamp":1695804587000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9004008\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9004008","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}