Summary
IEICE Information and Communication Technology Forum
2016
Session Number:B3
Session:
Number:B3-3
Evaluation of Classification Algorithms for Text Dependent and Text Independent Speaker Identification
Iosif Mporas, Saeid Safavi, Hock Chye Gan, Reza Sotudeh,
pp.-
Publication Date:2016-10-01
Online ISSN:2188-5079
DOI:10.34385/proc.24.B3-3
PDF download (153.3KB)
Summary:
We present a comparative evaluation of different classification algorithms for the task of speaker identity selection based on GMM-UBM speaker identification scores. The performance of the evaluated classification algorithms was examined in both text-dependent and text-independent operation modes for speaker identification. The experimental results indicated a significant improvement in terms of speaker identification accuracy, which was approximately 7% and 14.5% for the text-dependent and the text-independent scenarios, respectively.