Implementation of an intelligent system for estimation of fundamental frequency of speech

The analysis of fundamental frequency is very important in elementary speech processing. It helps in the reduction of harmonics of speech and distortions due to hum. In this paper, an intelligent controller, BELBIC, based on mammalian limbic Emotional Learning algorithms is used for the estimation of the fundamental speech frequency. BELBIC works on reinforced learning and is trained so as to extract the fundamental frequencies from the speech input. This is based on the instantaneous frequency estimation technique where true non-stationary property of speech is considered. The implementation of the proposed system is done using Simulink and the results have been included towards the end.