Speech enhancement combined with auditory perception masking in non-stationary noise environment

Aiming at the problem of residual noise,a modified speech enhancement algorithm combined with the masking properties of human auditory system was presented.A two-stage speech enhancement algorithm framework combined with MMSE-LSA spectral estimation method and an optimum perceptual enhancement filter was constructed,which effectively removed the residual noise using the masking properties.Detailed operation steps and the theoretical derivation of the perceptual enhancement filter were given out.Results of the simulation indicate the speech distortion and residual noise are significantly reduced in conditions of different kinds of non-stationary background noise,and the subjective and objective qualities are improved.