Generating intelligible audio speech from visual speech
- Submitting institution
-
The University of East Anglia
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 182621214
- Type
- D - Journal article
- DOI
-
10.1109/TASLP.2017.2716178
- Title of journal
- IEEE Transactions on Audio, Speech, and Language Processing
- Article number
- -
- First page
- 1447
- Volume
- 25
- Issue
- 9
- ISSN
- 1558-7916
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2017
- URL
-
-
- 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
-
1
- Research group(s)
-
-
- Citation count
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The technique of transforming visual speech into an audio signal that can be listened to is a new area of speech processing. This paper proposes a method to achieve this and demonstrates, using formal subjective tests, that an intelligible audio signal can be produced. The paper is significant as, to our knowledge, this is the first work to demonstrate that this can be done and has application in medical and security areas. We have worked with a government agency (name confidential) to consider how this can be exploited within surveillance applications where unlawful activities are being undertaken.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -