A novel blind source separation （BSS） algorithm based on the combination of negentropy and signal noise ratio （SNR） is presented to solve the deficiency of the traditional independent component analysis （ICA） al...A novel blind source separation （BSS） algorithm based on the combination of negentropy and signal noise ratio （SNR） is presented to solve the deficiency of the traditional independent component analysis （ICA） algorithm after the introduction of the principle and algorithm of ICA. The main formulas in the novel algorithm are elaborated and the idiographic steps of the algorithm are given. Then the computer simulation is used to test the performance of this algorithm. Both the traditional FastlCA algorithm and the novel ICA algorithm are applied to separate mixed signal data. Experiment results show the novel method has a better performance in separating signals than the traditional FastlCA algorithm based on negentropy. The novel algorithm could estimate the source signals from the mixed signals more precisely.展开更多
参考独立分量分析(independen t com ponen t ana lys is w ith reference,ICA-R)将源信号的先验知识以参考信号的形式引入学习算法中,可以从混合信号中仅抽取期望的源信号.基于ICA-R提出了一种语音增强新方法.通过比较语音信号和多种...参考独立分量分析(independen t com ponen t ana lys is w ith reference,ICA-R)将源信号的先验知识以参考信号的形式引入学习算法中,可以从混合信号中仅抽取期望的源信号.基于ICA-R提出了一种语音增强新方法.通过比较语音信号和多种噪声信号的特点,合理地构造了具有语音信号重要特性的参考信号,进而应用ICA-R从多种加性噪声中抽取了期望增强的语音信号.计算机仿真和性能分析结果均表明了该方法的有效性.展开更多
文摘A novel blind source separation （BSS） algorithm based on the combination of negentropy and signal noise ratio （SNR） is presented to solve the deficiency of the traditional independent component analysis （ICA） algorithm after the introduction of the principle and algorithm of ICA. The main formulas in the novel algorithm are elaborated and the idiographic steps of the algorithm are given. Then the computer simulation is used to test the performance of this algorithm. Both the traditional FastlCA algorithm and the novel ICA algorithm are applied to separate mixed signal data. Experiment results show the novel method has a better performance in separating signals than the traditional FastlCA algorithm based on negentropy. The novel algorithm could estimate the source signals from the mixed signals more precisely.
文摘参考独立分量分析(independen t com ponen t ana lys is w ith reference,ICA-R)将源信号的先验知识以参考信号的形式引入学习算法中,可以从混合信号中仅抽取期望的源信号.基于ICA-R提出了一种语音增强新方法.通过比较语音信号和多种噪声信号的特点,合理地构造了具有语音信号重要特性的参考信号,进而应用ICA-R从多种加性噪声中抽取了期望增强的语音信号.计算机仿真和性能分析结果均表明了该方法的有效性.
