{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:29:44Z","timestamp":1730197784081,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002385","name":"Ministry of Higher Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002385","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,31]]},"DOI":"10.1109\/apsipaasc58517.2023.10317456","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:07:46Z","timestamp":1700489266000},"page":"833-838","source":"Crossref","is-referenced-by-count":0,"title":["ELEGANT: End-to-end Language Grounded Speech Denoiser for Efficient Generation of Talking Face"],"prefix":"10.1109","author":[{"given":"Ai-Fang","family":"Chai","sequence":"first","affiliation":[{"name":"Monash University,CyPhi (ΨΦ) AI Lab, School of IT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sailaja","family":"Rajanala","sequence":"additional","affiliation":[{"name":"Monash University,CyPhi (ΨΦ) AI Lab, School of IT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arghya","family":"Pal","sequence":"additional","affiliation":[{"name":"Monash University,CyPhi (ΨΦ) AI Lab, School of IT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rapha\u00ebl C.-W.","family":"Phan","sequence":"additional","affiliation":[{"name":"Monash University,CyPhi (ΨΦ) AI Lab, School of IT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chee-Ming","family":"Ting","sequence":"additional","affiliation":[{"name":"Monash University,CyPhi (ΨΦ) AI Lab, School of IT"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2556","article-title":"Learning to see by looking at noise","volume":"34","author":"Jurjo","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00836"},{"key":"ref3","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"volume-title":"Silero models: pre-trained enterprise-grade stt \/ tts models and benchmarks","year":"2021","key":"ref4"},{"article-title":"Neural codec language models are zero-shot text to speech synthesizers","year":"2023","author":"Wang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414834"},{"article-title":"Obamanet: Photo-realistic lip-sync from text","year":"2017","author":"Kumar","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00515"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.518"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00483"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178767"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480484"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1130"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747236"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.556"}],"event":{"name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2023,10,31]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10317071\/10317095\/10317456.pdf?arnumber=10317456","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T16:27:02Z","timestamp":1710347222000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317456\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317456","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}