Efficient Parameterization for Automatic Speaker Recognition Using Support Vector Machines

Recent advances in the field of speaker recognition have proved to highly outperform algorithms. However this performance degrades when limited data are presented. This paper presents examples on how SVM can improve speaker recognition. The main contribution in this approach is the use of new low-di...

Full description

Saved in:
Bibliographic Details
Published inIntelligent Systems Design and Applications Vol. 557; pp. 659 - 666
Main Authors Chakroun, Rania, Frikha, Mondher, Zouari, Leila Beltaïfa
Format Book Chapter
LanguageEnglish
Published Switzerland Springer International Publishing AG 2017
Springer International Publishing
SeriesAdvances in Intelligent Systems and Computing
Subjects
Artificial intelligence
Limited data
Speaker identification
Speaker recognition
Support vector machines
Online AccessGet full text

Cover

More Information
Summary:Recent advances in the field of speaker recognition have proved to highly outperform algorithms. However this performance degrades when limited data are presented. This paper presents examples on how SVM can improve speaker recognition. The main contribution in this approach is the use of new low-dimensional vectors when training data are limited. We show how different kernels function of Support Vector Machines (SVM) can be used to deal a new approach for speaker recognition system. We achieved remarkable results using TIMIT database.
ISBN:9783319534794
3319534793
ISSN:2194-5357
2194-5365
DOI:10.1007/978-3-319-53480-0_65