Speaker recognition using PCA-based feature transformation
- Submitting institution
-
University of Portsmouth
- Unit of assessment
- 12 - Engineering
- Output identifier
- 14016916
- Type
- D - Journal article
- DOI
-
10.1016/j.specom.2019.04.001
- Title of journal
- Speech Communication
- Article number
- -
- First page
- 33
- Volume
- 110
- Issue
- -
- ISSN
- 0167-6393
- Open access status
- Access exception
- Month of publication
- April
- Year of publication
- 2019
- 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
-
3
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This study employs a novel feature processing method for the front-end of speaker recognition systems of use in banking systems worldwide. This paper is significant because it introduces a completely new paradigm to the statistical interpretation of the most important speech features which makes it applicable to more than just speaker recognition. Further recent developments have drawn inspiration from this approach for applications such as language and dialect discrimination (Miao et al. Circuits, Systems and Signal Processing, 2021).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -