Voice Recognition Technology Using Neural Networks

Journal Title: Journal of New technology and Materials - Year 2015, Vol 5, Issue 1

Abstract

This paper presents the use of a Multi-Layer Perceptron Neural Nets (MLP-NN) for voice recognition dedicated to generating robot commands. Our main goal concerns the estimation of the minimal number of elements required for the learning process in order to ensure an acceptable success of the neural nets recognition system. As the MLP requires references for the spoken words, we have provided these references by the means of a supervised classifier based on the mean square error. An experimental approach has been followed for the design of experiments enabling to determine the minimal elements in the sample for each voice command. Satisfactory results have been obtained leading to a better understanding of variability of the system functioning. Finally, we have noticed that the success rate of the MLP and the minimal number of elements used for the learning process depend on the spoken word structure and of the variability of the situation (word length, noise, speaker, etc). Keywords:;

Authors and Affiliations

Abdelouahab Zaatri, Norelhouda Azzizi, Fouad Lazhar Rahmani

Keywords

Related Articles

Numerical Analysis Of Turbulent Forced-Convection Flow In A Channel With Staggered L-Shaped Baffles

Characteristics of fluid flow and heat transfer are analyzed for a constant property fluid flowing turbulently through a two-dimensional horizontal rectangular cross section channel with staggered, transverse L-shaped ba...

Effectof aluminum carbide additives on carbothermic reduction process from alumina to aluminum

In terms of electricity consumption, the carbothermic reduction process of alumina (Al2O3) represents one of the promising candidates to overcome the current industrial Hall-Héroult process for the production of aluminum...

Conception and characterization of moleculary imprinted polymers nanofibers of poly(ethylene-co-vinyl alcohol) and their use as membrane inelectrochemical sensor for creatinine detection

We report on the deposition of molecularly imprinted polymer (MIP) nanofibers (NFs) by electrospinning and on their potentialities in electrochemical biosensors. Electrospun polymer was the copolymer poly(ethylene-co-vin...

Developing heat transfer in a solar air channel with arc-shaped baffles: effect of baffle attack angle

The current study illustrates a computational fluid dynamic analysis of 2D steady-state turbulent forced-convection flow and friction loss characteristics through a constant temperature-surfaced rectangular cross section...

Quartz sand beneficiation using magnetic and electrostatic separation to glass industries

Quartz sand of Fortuna formation was assigned to the Oligo-Miocene. This formation outcrops in Central Tunisia, particularly in the Ain Bou Morra area. The grain particle size ranges from fine to medium. The morphoscopic...

Download PDF file
  • EP ID EP268363
  • DOI -
  • Views 64
  • Downloads 0

How To Cite

Abdelouahab Zaatri, Norelhouda Azzizi, Fouad Lazhar Rahmani (2015). Voice Recognition Technology Using Neural Networks. Journal of New technology and Materials, 5(1), 27-31. https://europub.co.uk/articles/-A-268363