{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:59:02Z","timestamp":1775667542514,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096480","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":13,"title":["Period VITS: Variational Inference with Explicit Pitch Modeling for End-To-End Emotional Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Yuma","family":"Shirahata","sequence":"first","affiliation":[{"name":"LINE Corp.,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryuichi","family":"Yamamoto","sequence":"additional","affiliation":[{"name":"LINE Corp.,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eunwoo","family":"Song","sequence":"additional","affiliation":[{"name":"NAVER Corp.,Seongnam,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryo","family":"Terashima","sequence":"additional","affiliation":[{"name":"LINE Corp.,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jae-Min","family":"Kim","sequence":"additional","affiliation":[{"name":"NAVER Corp.,Seongnam,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kentaro","family":"Tachibana","sequence":"additional","affiliation":[{"name":"LINE Corp.,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"rezende","year":"2015","journal-title":"Proc ICML"},{"key":"ref12","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref15","article-title":"Chunked autoregressive GAN for conditional waveform synthesis","author":"morrison","year":"2022","journal-title":"Proc ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747664"},{"key":"ref30","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10294"},{"key":"ref10","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021","journal-title":"Proc ICML"},{"key":"ref2","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref1","author":"tan","year":"2021","journal-title":"A survey on neural speech synthesis"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-976"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414401"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11130"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2746264"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2076805"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682353"},{"key":"ref20","first-page":"901","article-title":"Period-HiFi-GAN: Fast and fundamental frequency controllable neural vocoder","author":"matsubara","year":"2022","journal-title":"Proc Acoustic Society of Japan"},{"key":"ref22","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"larsen","year":"2016","journal-title":"Proc ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref29","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"2020","journal-title":"Proc ICLR"},{"key":"ref8","article-title":"Fast- Speech 2: Fast and high-quality end-to-end text-to-speech","author":"ren","year":"2021","journal-title":"Proc ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","article-title":"End-to-end adversarial text-to-speech","author":"donahue","year":"2021","journal-title":"Proc ICLR"},{"key":"ref4","author":"van den oord","year":"2016","journal-title":"WaveNet A Generative Model for Raw Audio"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref6","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096480.pdf?arnumber=10096480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:57:01Z","timestamp":1699901821000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096480","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}