Lip Reading Sentences Using Deep Learning With Only Visual Cues
- Submitting institution
-
London South Bank University
- Unit of assessment
- 12 - Engineering
- Output identifier
- 288349
- Type
- D - Journal article
- DOI
-
10.1109/ACCESS.2020.3040906
- Title of journal
- IEEE Access
- Article number
- -
- First page
- 215516
- Volume
- 8
- Issue
- -
- ISSN
- 2169-3536
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2020
- URL
-
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9272286
- Supplementary information
-
-
- 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)
-
A - The BioEngineering Research Centre
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents the development of a neural network-based lip reading system, which has achieved a significantly improved performance with 15% lower word error rate, compared with the state-of-the-art lip reading systems, tested on the BBC Lip Reading Sentences 2 (LRS2) benchmark dataset. This paper is the result of PhD project work, and joint research collaboration between researchers in the UK and in China. The PhD work has generated several conference presentations and journal publications, and has attracted several internships from Polytech Nantes, France. The work has also generated a sponsored PhD studentship from British University in Egypt.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -