Speaker Identification using Hopfield Neural Network based Classifier

Authors

  • Md. Rabiul Islam (Dr. Md. Rabiul Islam) Associate Professor Dept. of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi-6204, Bangladesh. Mobile: +8801715418938
  • Md. Fayzur Rahman Professor Dept. of Electrical and Electronic Engineering Daffodil International University Dhaka, Bangladesh

Keywords:

Speaker Identification, Speech Start and end Points Detection, Speech Feature Extraction, Hopfield Neural Network.

Abstract

The aim of this work is to enhance the performance of speaker identification using Hopfield neural network algorithm. Speech signals are collected from VALID Audio-Visual dataset and some speech signal pre-processing techniques are applied to process the speech to feed the Hopfield neural network algorithm. Filtering technique is applied to remove the noises from the speech signals. MFCC based standard speech feature extraction technique is used to extract the speech features. These speech features are used for the learning and recognition model of Hopfield neural network. VALID audio-visual database has been used to measure the performance of the proposed system.

Keywords: Speaker identification, speech start and end points detection, speech feature extraction, Hopfield neural network

Cite this Article

Md. Rabiul Islam, Md. Fayzur Rahman. Speaker Identification using Hopfield Neural Network based Classifier. Journal of Network Security (JoNS). 2015; 3(2): 32–35p.


 

Published

2015-07-08

Issue

Section

Research Articles