Abstract

Speech Enhancement can be used as a preprocessing technique in any of the speech communication systems. Speech communication involves a speaker, listener and communication device. The background noise present in the speech signal while transmitting has to be removed from the noisy speech signal to increase the signal intelligibility and to minimize the listener fatigue. The proposed approach is a speech enhancement method based on the spectral subtraction method, and the preprocessing is done by using partial differential equation. This method provides a greater degree of flexibility and control on the noise subtraction levels that reduces artifacts in the enhanced speech, resulting in improved speech quality and intelligibility. This method can be applied as a speech enhancement technique in Digital hearing aids, where sensor neural loss patients need 5dB to 10 dB higher SNR than normal hearing subjects.