基于谱减法和变步长LMS语音增强算法

Speech enhancement algorithm based on spectral subtraction and variable-step LMS algorithm

谱减法是目前有效的增强语音信号质量的技术之一,低信噪比下降噪效果明显,而LMS自适应滤波算法收敛速度慢,步长需在收敛速度和失调折中选择。提出了先经过谱减法然后采用变步长LMS自适应滤波算法联合去噪来提高信号质量,通过改变误差的平方项来调节步长,步长采用先固定后变化的原则,兼顾了提高收敛速度和缩小稳态误差。在MATLAB环境下进行仿真实验,测试结果表明提出的经过基本谱减法后再采用变步长LMS自适应滤波算法能有效消除背景噪声,信噪比SNR和PESQ分值得到了较大的提高,减少了原始语音信号的失真,提高了信号质量。

Spectral subtraction is one of the effective technologies to enhance the quality of the voice signal, it has a good noise reduction effect at low SNR, the convergence rate and imbalance are effected by step size in LMS adaptive filtering algorithm. This paper introduces a method to enhance the quality of speech signal based on the combination of spectral subtraction and variable-step LMS adaptive filtering algorithm, to adjust the step size by changing the squared term of error, the step size follows the principle of change after the first fixed, achieves the purpose to improve the convergence rate and reduces the steady-state error. In MATLAB simulation environment, the experiments show that this method can effectively eliminate background noise, the SNR and PESQ scores are highly improved, the distortion of speech signal is reduced, and signal quality is improved.