The paper deals with the increasing accuracy of voice authentication methods. The developed algorithm first extracts segmental parameters, such as Zero Crossing Rate, the Fundamental Frequency and Mel-frequency cepstral coefficients from voice. Based on these parameters, the neural network classifier detects the speaker's emotional state. These parameters shape the distribution of neurons in Kohonen maps, forming clusters of neurons on the map characterizing a particular emotional state. Using regression analysis, we can calculate the function of the parameters of individual emotional states. This relationship increases voice authentication accuracy and prevents unjust rejection.

Date Published: 29 May 2013
PDF: 12 pages
Proc. SPIE 8750, Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XI, 875006 (29 May 2013); doi: 10.1117/12.2015719

Published in SPIE Proceedings Vol. 8750:
Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XI
Harold H. Szu, Editor(s)