Speaker identification through use of features selected using genetic algorithm
ELECTRONICS LETTERS, vol.34, no.1, pp.39-40, 1998 (SCI-Expanded, Scopus)
- Publication Type: Article / Article
- Volume: 34 Issue: 1
- Publication Date: 1998
- Doi Number: 10.1049/el:19980126
- Journal Name: ELECTRONICS LETTERS
- Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
- Page Numbers: pp.39-40
- Middle East Technical University Affiliated: No
Abstract
The authors introduce the use of a genetic algorithm in the reduction of a 24 parameter (12 LPC derived cepstral coefficients +12 Delta-cepstral coefficients) set to a five, six, seven, eight or ten parameter set, for each speaker in text-independent speaker identification. The experimental results show that there is similar to 5% increase in the recognition rate when the reduced set of parameters is used.