An Approach to Reduce Noise in Speech Signals Using an Intelligent System: BELBIC

The two widespread concepts of noise reduction algorithms could be observed are spectral noisesubtraction and adaptive filtering. They have the disadvantage that there is no parameter todistinguish between the speech and the noise components of same frequency. In this paper, anintelligent controller, BELBIC, based on mammalian limbic Emotional Learning algorithms is usedfor increasing the speech quality from a noisy environment. Here the learning ability to train thesystem to recognize and the output thus obtained would be the fundamental frequency of thespeech spectrum thus reducing the noise level to minimum. The parameters on which thereduction of noise from the input speech spectrum depends have also been studied. The realtime implementations have been done using Simulink and the results of the analysis thusobtained are included in the end.