Evaluating the effect of voice activity detection in isolated Yoruba word recognition system

Please use this identifier to cite or link to this item: http://repository.elizadeuniversity.edu.ng/jspui/handle/20.500.12398/614

Title:	Evaluating the effect of voice activity detection in isolated Yoruba word recognition system
Authors:	Aibinu, Abiodun M. Salami, Momoh-Jimoh E. Najeeb, Athaur R. Azeez, J. F. Rajin, Ataul K.
Keywords:	Speech recognition Feature extraction Speech Mel frequency cepstral coefficient Artificial neural networks Accuracy Training
Issue Date:	17-May-2011
Publisher:	IEEE
Citation:	Aibinu, A. M., Salami, M. E., Najeeb, A. R., Azeez, J. F., & Rajin, S. A. K. (2011, May). Evaluating the effect of voice activity detection in isolated Yoruba word recognition system. In 2011 4th International Conference on Mechatronics (ICOM) (pp. 1-5). IEEE.
Abstract:	This paper discusses and evaluates the effect of voice Activity Detection (VAD) in an isolated Yoruba word recognition system (IYWRS). The word database used in this paper are collected from 22 speakers by repeating the numbers 1 to 9 three times each. A hybrid configuration of Mel-Frequency Cepstral coefficient (MFCC) and Linear Predictive Coding (LPC) have been used to extract the features of the speech samples. Artificial Neural Network algorithms are then used to classify these features. An overall accuracy of about 60% has been achieved from the two proposed feature extraction methods.
URI:	10.1109/ICOM.2011.5937134 http://repository.elizadeuniversity.edu.ng/jspui/handle/20.500.12398/614
Appears in Collections:	Research Articles

Files in This Item:

File	Description	Size	Format
Evaluating the effect of voice activity detection in isolated Yoruba word recognition system.pdf	Abstract	267.07 kB	Adobe PDF	View/Open

EUSpace