{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T05:00:15Z","timestamp":1764997215322},"reference-count":41,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639647","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"274-281","source":"Crossref","is-referenced-by-count":14,"title":["Rhythm-Flexible Voice Conversion Without Parallel Data Using Cycle-GAN Over Phoneme Posteriorgram Sequences"],"prefix":"10.1109","author":[{"given":"Cheng-chieh","family":"Yeh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Po-chun","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ju-chieh","family":"Chou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin-shan","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3758\/BRM.41.2.385"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: trainable text-speech alignment using kaldi","author":"mcauliffe","year":"2017","journal-title":"Proceedings of Interspeech"},{"key":"ref33","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref32","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"arXiv preprint arXiv 1703 10593"},{"key":"ref31","article-title":"Fully character-level neural machine translation without explicit segmentation","author":"lee","year":"2016","journal-title":"arXiv preprint arXiv 1610 01292"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","year":"2017","author":"veaux","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"article-title":"The carnegie mellon pronouncing dictionary [cmudict. 0.6]","year":"2005","author":"weide","key":"ref34"},{"key":"ref10","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":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953090"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953215"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1043"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-116"},{"key":"ref16","article-title":"Voice conversion from unaligned corpora using variational autoencoding wasserstein generative adversarial networks","author":"hsu","year":"2017","journal-title":"arXiv preprint arXiv 1704 00849"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref18","article-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","author":"kaneko","year":"2017","journal-title":"arXiv preprint arXiv 1711 11585"},{"key":"ref19","article-title":"Voice conversion using sequence-to-sequence learning of context posterior probabilities","author":"miyoshi","year":"2017","journal-title":"arXiv preprint arXiv 1704 02360"},{"key":"ref28","article-title":"Stargan-vc: Non-parallel many-to-many voice conversion with star generative adversarial networks","author":"kameoka","year":"2018","journal-title":"arXiv preprint arXiv 1806 02169"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462342"},{"key":"ref3","article-title":"Gmm-based voice conversion applied to emotional speech synthesis","author":"kawanami","year":"2003","journal-title":"Eighth European Conference on Speech Communication and Technology"},{"key":"ref6","first-page":"11","article-title":"Acoustic transformations to improve the intelligibility of dysarthric speech","author":"rudzicz","year":"2011","journal-title":"Proceedings of the Second Workshop on Speech and Language Processing for Assistive Technologies Association for Computational Linguistics"},{"key":"ref29","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5923\/j.ajsp.20120205.06"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318526"},{"key":"ref20","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"arXiv preprint arXiv 1312 6114"},{"key":"ref22","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014","journal-title":"arXiv preprint arXiv 1411 1784"},{"key":"ref21","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref41","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462018"},{"key":"ref25","article-title":"Stargan: Unified generative adversarial networks for multidomain image-to-image translation","author":"choi","year":"2017","journal-title":"arXiv preprint arXiv 1711 09020"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2018,12,18]]},"location":"Athens, Greece","end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639647.pdf?arnumber=8639647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T08:08:19Z","timestamp":1643270899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639647\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639647","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}