International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 177 - Number 39 |
Year of Publication: 2020 |
Authors: Mowaffak O. A. Albaraq |
10.5120/ijca2020919880 |
Mowaffak O. A. Albaraq . Arabic Speech Recognition System through VQLBG and Euclidean Distance Algorithms using Matlab. International Journal of Computer Applications. 177, 39 ( Feb 2020), 28-33. DOI=10.5120/ijca2020919880
The goal of this paper is to create an Arabic Speech Recognition System, and apply it to a speech of an unknown words. The system has been developed for introducing a unique technique making interaction of human with a computer for natural language processing. In this paper 100 Arabic samples were recorded through a microphone and MFCC features of speech sample were calculated, Vector Quantization for mapping large feature vectors to finite cluster codewords, build trained codebook model for each word and VQLBG with Euclidean Distances used for recognition word according to distortions associated with features. This system provides a high accuracy in case of Arabic speech words.