A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild
- Submitting institution
-
The University of Bath
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 213132915
- Type
- E - Conference contribution
- DOI
-
10.1145/3394171.3413532
- Title of conference / published proceedings
- 28th ACM International Conference on Multimedia (ACM MM)
- First page
- 484
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- October
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3394171.3413532&file=3394171.3413532.mp4&download=true
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Demonstrates the practical ability to synchronise audio accurately with speech. Showed how an accurate lip-sync discriminator could be obtained and also provided a new evaluation framework for all works. The benchmark developed in this work has been incorporated as the standard benchmark by paperswithcode.com that benchmarks all computer vision works. This work has seen significant interest with more than 1100 users for the code in two months. The work has led to a $100k project between Huawei and IIT Hyderabad and ongoing discussions with Samsung Research USA and the UK startup Synths.AI.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -