Speaker identification using multimodal neural networks and wavelet analysis
- Submitting institution
-
University of Wolverhampton
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1295
- Type
- D - Journal article
- DOI
-
10.1049/iet-bmt.2014.0011
- Title of journal
- IET Biometrics
- Article number
- 1
- First page
- 18
- Volume
- 4
- Issue
- 1
- ISSN
- 2047-4938
- Open access status
- Out of scope for open access requirements
- Month of publication
- January
- Year of publication
- 2015
- 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
- Yes
- Number of additional authors
-
2
- Research group(s)
-
-
- Citation count
- 26
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper describes a system that combines multiple Neural Networks with wavelet analysis to identify a speaker from its voice regardless of the content. Through comprehensive testing using the GRID database, the proposed system improved the identification rate by 15% and reduced the identification time by 40% when compared to existing methods. This paper was awarded the 2017 Premium Award for Best Paper in the Institute of Engineering and Technology (IET) Biometrics (https://digital-library.theiet.org/journals/premium-awards#2017). Premium Awards are given by the IET to recognise the best research papers published over a two-year period prior to the award.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -