{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:47:50Z","timestamp":1778168870002,"version":"3.51.4"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"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":[[2022,10,16]]},"DOI":"10.1109\/icip46576.2022.9897436","type":"proceedings-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T21:27:24Z","timestamp":1667510844000},"page":"1086-1090","source":"Crossref","is-referenced-by-count":5,"title":["Autolv: Automatic Lecture Video Generator"],"prefix":"10.1109","author":[{"given":"Wenbin","family":"Wang","sequence":"first","affiliation":[{"name":"University of New South Wales,School of Computer Science and Engineering,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Song","sequence":"additional","affiliation":[{"name":"University of New South Wales,School of Computer Science and Engineering,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanjay","family":"Jha","sequence":"additional","affiliation":[{"name":"University of New South Wales,School of Computer Science and Engineering,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref2","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref4","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. ICML","author":"Wang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref7","first-page":"2415","article-title":"Efficient neural audio synthesis","volume-title":"Proc. ICML","author":"Kalchbrenner"},{"key":"ref8","first-page":"3680","article-title":"Fitting new speakers based on a short untranscribed sample","volume-title":"Proc. ICML","author":"Nachmani"},{"key":"ref9","article-title":"Deep speaker: an end-to-end neural speaker embedding system","author":"Li","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref11","first-page":"10 040","article-title":"Neural voice cloning with a few samples","volume-title":"Proc. NeurIPS","author":"Arik"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/su12083247"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24003\/emitter.v7i1.373"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2003.12.001"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054301"},{"key":"ref17","article-title":"Adadurian: Few-shot adaptation for neural text-to-speech with durian","author":"Zhang","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1510"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref24","first-page":"5998","article-title":"Obamanet: Photo-realistic lip-sync from text","volume-title":"Proc. NeurIPS Workshops","author":"Kumar"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref28","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. NeurIPS","author":"Vaswani"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00159"},{"key":"ref30","article-title":"How teaching changed in the (forced) shift to remote learning","volume":"22","author":"Lederman","year":"2020","journal-title":"Inside Higher Ed"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2830"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref33","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. NeurIPS","author":"Jia"},{"key":"ref34","article-title":"Sample efficient adaptive text-to-speech","volume-title":"Proc. ICLR","author":"Chen"}],"event":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","location":"Bordeaux, France","start":{"date-parts":[[2022,10,16]]},"end":{"date-parts":[[2022,10,19]]}},"container-title":["2022 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9897158\/9897159\/09897436.pdf?arnumber=9897436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:18:20Z","timestamp":1705958300000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9897436\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,16]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icip46576.2022.9897436","relation":{},"subject":[],"published":{"date-parts":[[2022,10,16]]}}}