一种自适应算法的语音信号盲分离

盲信号处理算法主要有批处理算法和自适应算法两类，本文导出了一种批处理和自适应相结合的快速独立分量分析（Fast Independent Component Analysis, Fast ICA）算法，将该算法应用于语音信号盲分离处理，通过综合实验，从分离前后的波形、频谱图和主要评价参数说明该算法具有良好的信号分离效果。与扩展联合对角化（The Joint Approximative Diagonalization ofEigenmatrix,JADE）算法和自然梯度（Natural Gradient,NG）算法比较， fast ICA算法具有更好的分离效果。 

Blind separation of speech signal based on an adaptive agorithm

The main types of blind signal processing algorithm are batch algorithm and adaptive agorithm. Combined with batch algorithm and adaptive agorithm, the fast independent component analysis algorithm for speech signal blind separation processing is presented in this paper. Through the comprehensive experiments, the results show that Fast ICA algorithm has good signal separation efficiency from the signal waveforms and spectrums before and after separation and the main evaluation parameters. Fast ICA algorithm has better separation efficiency than the joint approximative diagonalization of eigenmatrix algorithm and natural gradient algorithm.