关于噪声环境中语音信号盲分离的研究

研究了在噪声环境中进行语音信号盲分离的问题。为了解决由于噪声导致解混合系统性能发生严重恶化的问题，在不增加传感器数目的前提下，利用语音源信号的短时平稳特性和噪声信号的长时间平稳特性，给出差分方法可以抵消噪声信号的影响，使得解混合系统的权仍能够收敛。输入真实语音，通过计算机仿真验证了该算法的有效性。

The Study of Blind Speech Signal Separation in Noisy Environment

Authors is concerned with the speech signal separation in the noisy environment. In order to avoid the deteriorate of performance of unmixture system, we use the long-term nonstationarity of speech signals, as well as the long-term stationarity of noise signal, to cancel the effect that noise adds to unmixture system. Using the differential approach, the coefficients of the unmixture system can converge to their correct values. It's effectiveness is shown by means of computer simulation with real speech signals as their mixture inputs.