Phoneme-to-viseme mappings: the good, the bad, and the ugly
- Submitting institution
-
The University of East Anglia
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 182621251
- Type
- D - Journal article
- DOI
-
10.1016/j.specom.2017.07.001
- Title of journal
- Speech Communication
- Article number
- -
- First page
- 40
- Volume
- 95
- Issue
- -
- ISSN
- 0167-6393
- Open access status
- Access exception
- Month of publication
- December
- 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
- 11
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper puts selection of visual units on a firmer theoretical foundation and inter alia devises new methods for selecting visemes. It was part of a series of publications which led to the discovery of what was then the top-performing large vocabulary lip-reading system in the world (see, e.g., Thangthai and Harvey, “Building large-vocabuary speaker-independent lipreading systems", Interspeech 2018, pp 2648 –2652). Via presentation or personal contact this work has been picked up by Apple (invited talk), the UK spinout Liopa (employed a former team member) and with others via personal communication.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -