{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:55:36Z","timestamp":1753602936203},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022739","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"936-942","source":"Crossref","is-referenced-by-count":2,"title":["VTTS: Visual-Text To Speech"],"prefix":"10.1109","author":[{"given":"Yoshifumi","family":"Nakano","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takaaki","family":"Saeki","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katsuhito","family":"Sudoh","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8461368"},{"key":"ref4","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. NeurIPS","author":"Ren"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2467759"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2983298.2983305"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IPCC.2013.6623887"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34644-7_12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1236"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1148"},{"article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren","key":"ref11"},{"key":"ref12","first-page":"5167","article-title":"Style tokens: Unsuper-vised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. ICML","author":"Wang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2136"},{"key":"ref14","article-title":"Speech synthesis from text and ultrasound tongue image-based articulatory in-put","author":"Csapo","year":"2021","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2477"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053520"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.09.003"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45751-8_2"},{"key":"ref20","article-title":"Enriching word vectors with sub-word information","author":"Bojanowski","year":"2016","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.609"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6303"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1188"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4109"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-6245"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.576"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref29","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","volume-title":"Proc. ICML","author":"Nair"},{"key":"ref30","article-title":"JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis","author":"Sonobe","year":"2017","journal-title":"ar Xiv preprint"},{"volume-title":"KSS dataset: Ko-rean single speaker speech dataset","year":"2018","author":"Park","key":"ref31"},{"volume-title":"The LJSpeech dataset","year":"2017","author":"Ito","key":"ref32"},{"article-title":"manga2voice: speech analysis towards audio synthe-sis from comic image","volume-title":"Proc. 2020 Spring meeting of the Acoustical Society of Japan","author":"Takamichi","key":"ref33"},{"volume-title":"HMM-based speech synthesis system (HTS)","key":"ref34"},{"key":"ref35","first-page":"8588","article-title":"Investigating on in-corporating pretrained and learnable speaker represen-tations for multi-speaker multi-style text-to-speech","volume-title":"Proc. ICASSP","author":"Chien"},{"key":"ref36","first-page":"17022","article-title":"HiFi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","author":"Kong"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022739.pdf?arnumber=10022739","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:18:45Z","timestamp":1707805125000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022739\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022739","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}