{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T23:58:47Z","timestamp":1774742327533,"version":"3.50.1"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683282","type":"proceedings-article","created":{"date-parts":[[2019,4,16]],"date-time":"2019-04-16T16:07:22Z","timestamp":1555430842000},"page":"6805-6809","source":"Crossref","is-referenced-by-count":76,"title":["ATTS2S-VC: Sequence-to-sequence Voice Conversion with Attention and Context Preservation Mechanisms"],"prefix":"10.1109","author":[{"given":"Kou","family":"Tanaka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirokazu","family":"Kameoka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuhiro","family":"Kaneko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobukatsu","family":"Hojo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1142\/6192"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857790"},{"key":"ref33","article-title":"Sequence-to-sequence acoustic modeling for voice conversion","author":"zhang","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-247"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref30","first-page":"820","article-title":"Dual learning for machine translation","author":"he","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref36","article-title":"Phonetic posterior-grams for many-to-one voice conversion without parallel data training","author":"lifa","year":"2016","journal-title":"ICME"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041699"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref28","article-title":"Online and linear-time attention by enforcing monotonic alignments","author":"raffel","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462018"},{"key":"ref1","article-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","author":"kaneko","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref22","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref21","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref51","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"CoRR"},{"key":"ref52","article-title":"Convs2s-vc: Fully convolutional sequence-to-sequence voice conversion","author":"kameoka","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1587\/transfun.E96.A.1946"},{"key":"ref40","first-page":"2446","article-title":"Eigenvoice conversion based on gaussian mixture model","author":"tomoki","year":"2006","journal-title":"InterSpeech"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E97.D.1403"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2017EDL8034"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref18","article-title":"High-order sequence modeling using speaker-dependent recurrent temporal restricted boltzmann machines for voice conversion","author":"nakashika","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref19","first-page":"1","article-title":"Voice conversion from non-parallel corpora using variational auto-encoder","author":"hsu","year":"2016","journal-title":"Signal and Information Processing Association Annual Summit and Conference (APSIPA) 2016 Asia-Pacific"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1109\/SLT.2018.8639535","article-title":"StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks","author":"kameoka","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.09.006"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.11.004"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205241"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-522"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-970"},{"key":"ref46","article-title":"Tacotron speech synthesis implemented in tensorflow","author":"keith","year":"0"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref48","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2016"},{"key":"ref47","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)"},{"key":"ref42","article-title":"The CMU Arctic speech databases","author":"kominek","year":"2004","journal-title":"Proc Fifth ISCA Speech Synthesis Workshop"},{"key":"ref41","article-title":"One-to-many voice conversion based on tensor representation of speaker space","author":"saito","year":"2011","journal-title":"Twelfth Annual Conference of the International Speech Communication Association"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-33"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-29"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683282.pdf?arnumber=8683282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T23:14:20Z","timestamp":1657840460000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683282\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683282","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}