A Combined Approach to Text-Dependent Speaker Identification: Comparison with Pure Neural Net Approaches
Publication Type
Journal Article
Publication Date
1998
Abstract
A novel approach to automatic speaker identification (ASI) is presented. Most of the present automatic speaker identification systems based on neural networks have no definite mechanisms to compensate for time distortions due to elocution. Such models have less precise information about the intraspeaker measure. The new combined approach uses both distortion-based and discriminant-based methods. The distortion-based and discriminant-based methods are dynamic time warping (DTW) and artificial neural network (ANN) respectively. This paper compares this new classifier with a pure neural net classifier for speaker identification. The performance of the combined classifier surpasses that of a pure ANN classifier for the conditions tested.
Discipline
Artificial Intelligence and Robotics
Publication
Journal of Circuits, Systems and Computers
Volume
8
Issue
2
First Page
273
Last Page
281
ISSN
0218-1266
Identifier
10.1142/S0218126698000110
Publisher
World Scientific Publishing
Citation
LIANG, Qianhui (Althea) and ZHU, Miao-Liang.
A Combined Approach to Text-Dependent Speaker Identification: Comparison with Pure Neural Net Approaches. (1998). Journal of Circuits, Systems and Computers. 8, (2), 273-281.
Available at: https://ink.library.smu.edu.sg/sis_research/1095
Additional URL
http://dx.doi.org/10.1142/S0218126698000110