Modulation Components and Genetic Algorithm for Speaker Recognition System

Abstract

In this paper, the aim is to investigate weather or not that changing the filter-bank components (of the speaker recognition system) could improve the system performance in identifying the speaker. The filter is composed of 30 Gamatone filter channels. First, the channels are mel distributed of the frequency line. Then the components´values (center frequencies and bandwidths) changes with each run. Genetic algorithm (GA) is adopted to improve the filter component values that, in a result, improve the system performance. At each GA run, a new set of filter components will be generated that aimed to improve the performance comparing with the previous run. This will continue until the system reach to the maximum accuracy or the GA reach to its limits. Results show that the system will be improved at each run, however, different words might response differently to the system filter changing. Also, in terms of additive noise, the results show that although the digits affected differently by the noise, the system still get improving with reach GA run.

Authors and Affiliations

Tariq A. Hassan, Rihab I. Ajel, Eman K. Ibrahim

Keywords

Related Articles

Pattern Visualization Through Detection Plane Generation for Macroscopic Imagery

Macroscopic images are kind of environments in which complex patterns are present. Satellite images are one of these classes where many patterns are present. This fact reflects the challenges in detecting patterns presen...

Moving from Heterogeneous Data Sources to Big Data: Interoperability and Integration Issues

Heterogeneous databases now facing an emerging challenge of moving towards big data. These databases are adhoc polyglot systems, complex, and NoSQL tools which are semantically annotated. Integration of these heterogeneo...

A New Optimum Frequency Controller of Hybrid Pumping System: Bond Graph Modeling-Simulation and Practice with ARDUINO Board

The strategy of rural development in Tunisia needs to include as one of its priorities: the control of water. In seeking solutions for the energy control dedicated to pumping, it seems interesting to know the benefits of...

Numerical Simulation on Damage Mode Evolution in Composite Laminate

The present work follows numerous numerical simulation on the stress field analysis in a cracked cross-ply laminate. These results lead us to elaborate an energy criterion. This criterion is based on the computation of t...

Clustering based Max-Min Scheduling in Cloud Environment

Cloud Computing ensures Service Level Agreement (SLA) by provisioning of resources to cloudlets. This provisioning can be achieved through scheduling algorithms that properly maps given tasks considering different heuris...

Download PDF file
  • EP ID EP259154
  • DOI 10.14569/IJACSA.2017.080569
  • Views 69
  • Downloads 0

How To Cite

Tariq A. Hassan, Rihab I. Ajel, Eman K. Ibrahim (2017). Modulation Components and Genetic Algorithm for Speaker Recognition System. International Journal of Advanced Computer Science & Applications, 8(5), 557-561. https://europub.co.uk/articles/-A-259154