Automatic speaker, age-group and gender identification from children's speech
- Submitting institution
-
The University of Birmingham
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 73270604
- Type
- D - Journal article
- DOI
-
10.1016/j.csl.2018.01.001
- Title of journal
- Computer Speech and Language
- Article number
- -
- First page
- 141
- Volume
- 50
- Issue
- -
- ISSN
- 0885-2308
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2018
- 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
-
2
- Research group(s)
-
-
- Citation count
- 14
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is the first systematic study of speech detection technologies for children’s speech, specifically age, gender and speaker identification. Computer analysis of child speech is especially challenging because of increased variability due to dynamic, age-dependent physiological and cognitive factors. Results demonstrate that detection technologies are viable for children provided these and other issues, such as the onset of puberty, are properly accommodated. This research is important and timely. Its potential impact addresses urgent contemporary challenges including online child protection (to verify the profile of an individual that a child interacts with remotely), and personalisation of online education resources.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -