基于信号子空间的语音增强方法

基于子空间的语音增强算法不同于基于信号处理和统计估计的经典语音增强算法,其核心思想就是将带噪语音信号映射到信号子空间和噪声子空间中,并在信号子空间中估计原始信号。本文提出的算法是以线性代数和矩阵分析为基础,利用对语音信号和噪声协方差矩阵同时对角变换的条件,对混有加性白噪声和粉红噪声的语音信号进行增强处理。经过实验分析及与传统的语音增强算法相比较,语音失真较小,增强效果较好,能够在极大限度地抑制背景噪声的同时减少频谱失真和残余噪声。

Speech enhancement method based on the signal subspace

The speech enhancement algorithm based on the signal subspace is different from the classic speech enhancement algorithm based on signal processing and statistical estimates.This paper proposes a speech enhancement method based on signal subspace.This method is based on linear algebra and matrix analysis,uses conditions of speech signal and noise covariance matrix and diagonal transform,processes the enhancement of mixture of white noise and pink noise voice signal.Compared through experimental analysis and enhancement algorithms with the traditional voice,it has a smaller distortion,and a better enhancement effect,greatly limits to suppress background noise while reducing the spectral distortion and residual noise.