RESEARCH OF SPEECH ENHANCEMENT BASED ON AUDITORY MODEL

摘要

We propose a speech enhancement method based on the auditory model in this paper in order to improve the quality of the speech in the environment of the low SNR.Low SNR noisy speech is proposed by the auditory nerve model to enhance the higher SNR speech.The results show that the method reduces the target speech signal distortion, compared with the traditional spectral subtraction, the subjective and objective hearing have shown significant improvement.