Open AccessSpeech Recognition Using Combined Fuzzy and Ant Colony algorithm
Author(s) -
Fooad Jalili,
Milad Jafari Barani
Publication year - 2016
Publication title -
international journal of electrical and computer engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.277
H-Index - 22
ISSN - 2088-8708
DOI - 10.11591/ijece.v6i5.pp2205-2210
Subject(s) - computer science , speech recognition , noise (video) , fuzzy logic , pattern recognition (psychology) , signal (programming language) , set (abstract data type) , artificial intelligence , ant colony optimization algorithms , algorithm , image (mathematics) , programming language
In recent years various methods has been proposed for speech recognition and removing noise from the speech signal became an important issue. In this paper a fuzzy system has been proposed for speech recognition that can obtain accurate results using classification of speech signals with “Ant Colony” algorithm. First, speech samples are given to the fuzzy system to obtain a pattern for every set of signals that can be helpful for dimensionality reduction, easier checking of outcome and better recognition of signals. Then, the “ACO” algorithm is used to cluster these signals and determine a cluster for each input signal. Also, with this method we will be able to recognize noise and consider it in a separate cluster and remove it from the input signal. Results show that the accuracy for speech detection and noise removal is desirable.