Title :
Tips on speaker recognition by autoregressive parameters and connectionist methods
Author :
Costin, Madalin ; Grichnik, A. ; Zbancioc, Marius
Abstract :
This study reveals more interesting aspects on speaker and speech recognition as: 1. different importance of certain spectral frequency bands on the process of speaker and speech recognition; 2. signal phase has a significant importance; and 3. vowel recognition is preponderant in the decision weighting. To resolve the paradox described in A.J. Grichnik (2000), autoregressive (AR) coefficients were used to compute feature vectors in order to teach neural networks (NN). Tests made by using a two layer perceptron (MLP) were compared to a radial basis function (RBF) network in order to obtain the best recognition results.
Keywords :
autoregressive processes; multilayer perceptrons; radial basis function networks; speaker recognition; MLP; RBF; autoregressive parameters; connectionist methods; decision weighting; feature vectors; multilayer perceptron; neural networks; radial basis function; signal phase; speaker recognition; spectral frequency bands; speech recognition; two layer perceptron; vowel recognition;
Conference_Titel :
Signals, Circuits and Systems, 2003. SCS 2003. International Symposium on
Print_ISBN :
0-7803-7979-9
DOI :
10.1109/SCS.2003.1226975
