{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:02:07Z","timestamp":1776884527552,"version":"3.51.2"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JST"},{"name":"CREST","award":["JPMJCR19A3"],"award-info":[{"award-number":["JPMJCR19A3"]}]},{"name":"JSPS KAKENHI","award":["17H06101"],"award-info":[{"award-number":["17H06101"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3049336","type":"journal-article","created":{"date-parts":[[2021,1,5]],"date-time":"2021-01-05T22:53:17Z","timestamp":1609887197000},"page":"745-755","source":"Crossref","is-referenced-by-count":38,"title":["Pretraining Techniques for Sequence-to-Sequence Voice Conversion"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3172-3335","authenticated-orcid":false,"given":"Wen-Chin","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8782-4093","authenticated-orcid":false,"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4390-1354","authenticated-orcid":false,"given":"Yi-Chiao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3102-0162","authenticated-orcid":false,"given":"Hirokazu","family":"Kameoka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","article-title":"Large batch optimization for deep learning: Training bert in 76 minutes","author":"you","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref70","article-title":"Munich Artificial Intelligence Laboratories GmbH, the M-AILABS Speech Dataset","year":"2019"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref75","article-title":"Wavenet: A generative model for raw","author":"oord","year":"2016"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001456"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2665"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2960721"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1789"},{"key":"ref35","article-title":"Taco-vc: A. single speaker tacotron based voice conversion with limited data","author":"leshem","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1778"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref62","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2380"},{"key":"ref64","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref65","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3034994"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref69","first-page":"223","article-title":"The CMU ARCTIC speech databases","author":"kominek","year":"0","journal-title":"Proc 5th Ind Sci Cong Assoc Workshop Speech Synth"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref21","first-page":"694","article-title":"Perceptual losses for real-time style transfer and super-resolution","author":"johnson","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref24","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref26","article-title":"Language models are unsupervised multitask learners","author":"radford","year":"2019"},{"key":"ref25","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1514"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683746"},{"key":"ref59","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref58","article-title":"Hierarchical sequence to sequence voice conversion with limited data","author":"narayanan","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-247"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1542"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004008"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1357"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659543"},{"key":"ref52","article-title":"Multi-target emotional voice conversion with neural vocoders","author":"liu","year":"2020"},{"key":"ref10","first-page":"4676","article-title":"Voice transformer network: Sequence-to-sequence voice conversion using transformer with text-to-speech pretraining","author":"huang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682380"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref13","first-page":"3320","article-title":"How transferable are features in deep neural networks","author":"yosinski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","first-page":"647","article-title":"DeCAF: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"0","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref82","first-page":"1","article-title":"Many-to-many voice transformer network","author":"kameoka","year":"2020","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref81","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref80","article-title":"Subjective evaluation of speech quality with a crowdsourcing approach","volume":"808","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref6","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref5","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820901"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref46","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.213"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref47","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"0","journal-title":"Proc Int Conf Learn Representation"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3232"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09314100.pdf?arnumber=9314100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T20:00:22Z","timestamp":1639771222000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9314100\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3049336","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}