잡음환경에서 음성강조를 위한 시간지연 신경회로망의 구현

Abstract

This paper proposes a speech enhancement system using a time-delay neural network, which implements the mapping from the space of speech signal degraded by noise to the space of clean speech signal. It is confirmed that this method is effective for speech degraded by white noise using the speech enhancement system, which restores the amplitude component of fast Fourier transform. The experimental results showed 14.9 % better then wiener filter at 5dB Noisy Environments.