Ability of Evolutionary and Recurrent SOM model GA-RSOM in Phonemic Recognition Optimization

Journal Title: INTERNATIONAL JOURNAL OF MATHEMATICS TRENDS AND TECHNOLOGY - Year 2013, Vol 4, Issue 6

Abstract

 The phoneme recognition aims to process a speech signal, characterized by a non-linearity with very high dynamics, allowing to perform various tasks on an information processing machine by an operator using orally address. This paper focuses on a proposed strategy, which implements an evolutionary recurrent self organizing map (SOM) model in phonemes recognition to improve their rates. It is a hybrid model (GARSOM) reflecting the approaches of K-means mobile centers, the evolutionary genetic algorithm (GA) principle and the recurrent temporal appearance of Kohonen map (RSOM) to be a powerful optimization tool for phonemic recognition, even in adverse environmental conditions.

Authors and Affiliations

Mohamed Salah Salhi ; Najet Arous; Noureddine Ellouze

Keywords

Related Articles

 Transmission Mechanisms of the Inequality-Growth Relationship

 This paper contributes to the debate over the relationship between income inequality and economic growth by developing a comprehensive description of the mechanisms and the models proposed in the literature over th...

Pulsatile Flow of Blood with Volume Fraction of Micro-organisms in the Presence of Transverse Magnetic Field through Stenosed Tube

This paper presents an analytical study of pulsatile flow of blood with micro-organisms through stenosed tubes in presence of transverse magnetic field.The effect of externally applied magnetic field on velocity, flow ra...

Separation Axioms in Intuitionistic Fuzzy Soft Topological space

In this paper, I have studied some properties of fuzzy soft topological space. We define fuzzy soft intuitionistic separation axioms and basic definition of intuitionistic fuzzy soft normal spaces and theorems. Lastly, i...

On wgrα - Homeomorphisms in Topological Spaces

A bijection f: (X, τ) → (Y, σ) is called weakly generalized regular α- homeomorphism if f and f-1are wgrα-continuous. Also we introduce the new class of maps, namely wgrαc-homeomorphisms which form a subclass of wgrα-ho...

 Tripled Fixed Point for Compatible mappings in Partially Ordered Fuzzy Metric Spaces

 In this paper we prove a tripled coincidence point theorem for compatible mapping in fuzzy metric space. Our aim of this paper is to improve the result of "A. Roldan, J. M. Moreno, C. Roldan," Tripled fixed point t...

Download PDF file
  • EP ID EP157070
  • DOI -
  • Views 76
  • Downloads 0

How To Cite

Mohamed Salah Salhi ; Najet Arous; Noureddine Ellouze (2013).  Ability of Evolutionary and Recurrent SOM model GA-RSOM in Phonemic Recognition Optimization. INTERNATIONAL JOURNAL OF MATHEMATICS TRENDS AND TECHNOLOGY, 4(6), 97-106. https://europub.co.uk/articles/-A-157070