{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:25:43Z","timestamp":1725686743508},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683872","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"6795-6799","source":"Crossref","is-referenced-by-count":3,"title":["Audiovisual Speaker Conversion: Jointly and Simultaneously Transforming Facial Expression and Acoustic Characteristics"],"prefix":"10.1109","author":[{"given":"Fuming","family":"Fang","sequence":"first","affiliation":[]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[]},{"given":"Isao","family":"Echizen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3241911"},{"key":"ref12","article-title":"Obamanet: Photo-realistic lip-sync from text","author":"kumar","year":"2017","journal-title":"31st Conference on Neural Information Processing Systems (NIPS 2017)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref15"},{"key":"ref16","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539957"},{"journal-title":"Audio-Visual Biometrics and Forgery","year":"2011","author":"greige","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462342"},{"key":"ref3","article-title":"Multimodal speaker identity conversion - continued -","author":"markaki","year":"2007","journal-title":"Proceedings of the eN-TERFACE07 Workshop on Multimodal Interfaces"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2286"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2210876"},{"article-title":"Visual speech enhancement using noise-invariant training","year":"2017","author":"gabbay","key":"ref8"},{"key":"ref7","first-page":"1247","article-title":"Deep canonical correlation analysis","author":"andrew","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2516"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1250\/ast.11.71"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"xu","year":"2015","journal-title":"ICML Deep Learning Workshop"},{"key":"ref21","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1227"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(97)80111-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref25","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"ICLRE"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683872.pdf?arnumber=8683872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:14:24Z","timestamp":1657854864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683872","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}