Conference item
You said that?
- Abstract:
- We present a method for generating a video of a talking face. The method takes as inputs: (i) still images of the target face, and (ii) an audio speech segment; and outputs a video of the target face lip synched with the audio. The method runs in real time and is applicable to faces and audio not seen at training time. To achieve this we propose an encoder-decoder CNN model that uses a joint embedding of the face and audio to generate synthesised talking face video frames. The model is trained on tens of hours of unlabelled videos. We also show results of re-dubbing videos using speech from a different perso
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
- Publisher:
- British Machine Vision Association and Society for Pattern Recognition
- Host title:
- 28th British Machine Vision Conference, 2017, Imperial College London, 4th-7th September 2017
- Journal:
- British Machine Vision Conference, 2017 More from this journal
- Publication date:
- 2017-09-04
- Acceptance date:
- 2017-07-01
- Pubs id:
-
pubs:742559
- UUID:
-
uuid:79911294-b5c8-48f2-a716-7f66e9685b28
- Local pid:
-
pubs:742559
- Source identifiers:
-
742559
- Deposit date:
-
2017-11-03
Terms of use
- Copyright holder:
- © 2017, Chung, Jamaludin, Zisserman
- Copyright date:
- 2017
- Notes:
- This is the publisher's version of the article. The final version is available online from The British Machine Vision Association and Society for Pattern Recognition at: https://bmvc2017.london/
If you are the owner of this record, you can report an update to it here: Report update to this record