{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T05:27:49Z","timestamp":1738128469567,"version":"3.33.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10849007","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Bluemarble: Bridging Latent Uncertainty in Articulatory-to-Speech Synthesis with a Learned Codebook"],"prefix":"10.1109","author":[{"given":"Seyun","family":"Um","sequence":"first","affiliation":[{"name":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miseul","family":"Kim","sequence":"additional","affiliation":[{"name":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Doyeon","family":"Kim","sequence":"additional","affiliation":[{"name":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong-Goo","family":"Kang","sequence":"additional","affiliation":[{"name":"Yonsei University,Department of Electrical and Electronic Engineering,Seoul,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2484"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3134563"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ab0c59"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/BHI58575.2023.10313388"},{"key":"ref5","first-page":"31","article-title":"Mapping from articulatory movements to vocal tract spectrum with gaussian mixture model for articulatory speech synthesis","volume-title":"ISCA Workshop on Speech Synthesis","author":"Toda"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743748"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.02.003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.23"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10892"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095404"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097120"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Chunked autoregressive gan for conditional waveform synthesis","volume-title":"ICLR","author":"Morrison","key":"ref14"},{"article-title":"Unsupervised learning of video representations using lstms","volume-title":"ICLR","author":"Srivastava","key":"ref15"},{"article-title":"Deep multi-scale video prediction beyond mean square error","volume-title":"ICLR","author":"Mathieu","key":"ref16"},{"key":"ref17","article-title":"Action-conditional video prediction using deep networks in atari games","volume-title":"NIPS","volume":"28","author":"Oh"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref19","first-page":"17 022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"NIPS","volume":"33","author":"Kong"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5334\/labphon.237"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980335"},{"key":"ref22","first-page":"837","article-title":"Personalized end-to-end mandarin speech synthesis using small-sized corpus","volume-title":"APSIPA ASC","author":"Yuan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"volume-title":"ICLR","key":"ref25","article-title":"CLam-TTS: Improving neural codec language model for zero-shot text-to-speech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3308474"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"article-title":"Taming visually guided sound generation","volume-title":"BMVC","author":"Iashin","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.7488\/ds\/2645"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2382"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10849007.pdf?arnumber=10849007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:23:54Z","timestamp":1738045434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849007\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10849007","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}