{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:44:17Z","timestamp":1776883457480,"version":"3.51.2"},"reference-count":24,"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\/icassp49357.2023.10095404","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["Style Modeling for Multi-Speaker Articulation-to-Speech"],"prefix":"10.1109","author":[{"given":"Miseul","family":"Kim","sequence":"first","affiliation":[{"name":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Piao","sequence":"additional","affiliation":[{"name":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jihyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong-Goo","family":"Kang","sequence":"additional","affiliation":[{"name":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2484"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-012-0109-x"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"6056","DOI":"10.3390\/s22166056","article-title":"Speaker adaptation on articulation and acoustics for articulation-to-speech synthesis","volume":"22","author":"cao","year":"2022","journal-title":"SENSORS"},{"key":"ref23","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1031"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-999"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref11","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"The lj speech dataset","author":"ito","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.23"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008228"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0196-0709(82)80025-2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401485"},{"key":"ref17","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1630"},{"key":"ref19","first-page":"7748","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","author":"min","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref18","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639213"},{"key":"ref7","article-title":"Mapping from articulatory movements to vocal tract spectrum with gaussian mixture model for articulatory speech synthesis","author":"toda","year":"2004","journal-title":"Fifth ISCA workshop on speech synthesis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-32"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1119-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.403997"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-010-1829-6_11"}],"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\/10095404.pdf?arnumber=10095404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:59:55Z","timestamp":1699883995000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095404\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095404","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}