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.