Charles, J, Magee, D orcid.org/0000-0003-2170-3103 and Hogg, D orcid.org/0000-0002-6125-9564 (2016) Virtual Immortality: Reanimating Characters from TV Shows. In: Hua, G and Jégou, H, (eds.) Lecture Notes in Computer Science. European Conference on Computer Vision, 08-16 Oct 2016, Amsterdam, The Netherlands. Lecture Notes in Computer Science (LNCS), 9915 . Springer Nature , pp. 879-886. ISBN 978-3-319-49408-1
Abstract
The objective of this work is to build virtual talking avatars of characters fully automatically from TV shows. From this unconstrained data, we show how to capture a character’s style of speech, visual appearance and language in an effort to construct an interactive avatar of the person and effectively immortalize them in a computational model. We make three contributions (i) a complete framework for producing a generative model of the audiovisual and language of characters from TV shows; (ii) a novel method for aligning transcripts to video using the audio; and (iii) a fast audio segmentation system for silencing non-spoken audio from TV shows. Our framework is demonstrated using all 236 episodes from the TV series Friends (≈ 97 h of video) and shown to generate novel sentences as well as character specific speech and video.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © Springer International Publishing 2016. This is an author produced version of a paper published in ECCV Workshops (3) , Lecture Notes in Computer Science. The final publication is available at Springer via https://doi.org/10.1007/978-3-319-49409-8 Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | Visual speech, video synthesis, video alignment |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Funding Information: | Funder Grant number EPSRC (Engineering and Physical Sciences Research Council) EP/I01229X/1 |
Depositing User: | Symplectic Publications |
Date Deposited: | 26 Apr 2018 12:06 |
Last Modified: | 23 May 2022 14:29 |
Status: | Published |
Publisher: | Springer Nature |
Series Name: | Lecture Notes in Computer Science (LNCS) |
Identification Number: | 10.1007/978-3-319-49409-8_71 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:130121 |