{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T16:12:42Z","timestamp":1772122362383,"version":"3.50.1"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T00:00:00Z","timestamp":1704672000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T00:00:00Z","timestamp":1704672000000},"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":[[2024,1,8]]},"DOI":"10.1109\/sii58957.2024.10417556","type":"proceedings-article","created":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T13:22:18Z","timestamp":1707484938000},"page":"153-158","source":"Crossref","is-referenced-by-count":1,"title":["Synthesis of Speech Reflecting Features from Lip Images"],"prefix":"10.1109","author":[{"given":"Atsushi","family":"Matsuura","sequence":"first","affiliation":[{"name":"Shibaura Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sota","family":"Shimizu","sequence":"additional","affiliation":[{"name":"Shibaura Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Chorowski","year":"2015","journal-title":"Attention-Based Models for Speech Recognition"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9054556"},{"key":"ref5","article-title":"Speech synthesis learning with Python","author":"Yamamoto","year":"2021","journal-title":"Impress Corporation"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref7","author":"Van Den Oord","year":"2016","journal-title":"WaveNet: A generative model for raw audio"},{"key":"ref8","first-page":"2056","article-title":"Speech synthesis from image characters","volume-title":"Proc. of Annual Conference of Information Processing Society of Japan (in Japanese)","author":"Nakano","year":"2022"},{"key":"ref9","volume-title":"Deep learning from scratch","author":"Saito","year":"2016"},{"key":"ref10","volume-title":"Deep learning from scratch 2","author":"Saito","year":"2018"},{"key":"ref11","volume-title":"I looked into Tacotron 2 \u2013 3","year":"2023"},{"key":"ref12","volume-title":"Introduction to Object Detection and GAN, Autoencoder, Image Processing, Shuwa System (in Japanese)","year":"2021"},{"key":"ref13","volume-title":"Explanation of acoustic features \u201cMel Spectrum\u201d and \u201cMel Frequency Cepstrum Coefficient (MFCC)\u201d and introduction of actual examples","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414901"}],"event":{"name":"2024 IEEE\/SICE International Symposium on System Integration (SII)","location":"Ha Long, Vietnam","start":{"date-parts":[[2024,1,8]]},"end":{"date-parts":[[2024,1,11]]}},"container-title":["2024 IEEE\/SICE International Symposium on System Integration (SII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10417130\/10417144\/10417556.pdf?arnumber=10417556","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T07:58:16Z","timestamp":1707811096000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10417556\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,8]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/sii58957.2024.10417556","relation":{},"subject":[],"published":{"date-parts":[[2024,1,8]]}}}