Title :
Neural network for single phoneme recognition based on mel-frequency cepstral coefficients coding
Author_Institution :
Faculty of Electrical Engineering, University of Banja Luka
Abstract :
This paper proposes novel approach in coding single phonemes based on mel-frequency cepstral coefficients (MFCC) in order to simplify the neural network used to recognize those phonemes. The efficiency and effectiveness of proposed algorithm are demonstrated for both male and female speakers.
Keywords :
"Cepstrum","Artificial neural networks","Encoding","Neurons","Mel frequency cepstral coefficient","Speaker recognition"
Conference_Titel :
Neural Network Applications in Electrical Engineering (NEUREL), 2010 10th Symposium on
Print_ISBN :
978-1-4244-8821-6
DOI :
10.1109/NEUREL.2010.5644071
