Text-Dependent Speaker Verification System Using Neural Network.

S. O. Kassim, C. Anene · 2015

This paper presents the use of back propagation neural network to implement voice recognition. The focus is to identify voice patterns of different people so as to recognize their voices electronically. The signals corresponding to a text phrase of a group of people are recorded in voice files on a computer using sound recording software. The information in these files is converted from time domain to frequency domain using digital signal processing techniques. The resulting preprocessed signal samples in frequency domain are then used to train a neural network to identify them from among other voice samples. Keywords-Back-propagation, feature extraction, feed-forward neural network, FFT, similarity analysis, spectral density.

Read the paper · More papers on PaperTik