An auditory-based adaptive speech enhancement system by neural network according to noise intensity

This paper presents an adaptive optimization method applying the auditory mechanism which is called lateral inhibition. This method first estimates noise intensity using a neural network, then adjusts adaptively the coefficients of both lateral inhibition and amplitude component according to the noise intensity for each input frame. It is confirmed that this method is effective for speech degraded not only by white noise but also by colored noise, judging from spectral distortion measurement