This paper proposes a new speech enhancement scheme based on modified Minimum MeanSquareError (MMSE) estimation of speech Short Time Spectrum Amplitude (STSA).
本文提出了一种改进型语音短时谱最小均方误差(MMSE)估计的增强方法。
2
However, two-stage estimates of regression coefficients corresponding to these two estimates have approximate equal meansquareerror.
对应于方差参数这两种估计的回归系数的两种两步估计,它们的均方误差大致相当。
3
The results of the test data indicate that the prediction system is reliable and the root ofmeansquareerror is about 15%.