一种基于MVDR的改进型麦克风阵列语音增强算法

An improved speech enhancement algorithm for microphone arrays based on MVDR

传统的最小方差无失真响应(Minimum Variance Distortionless Response,MVDR)波束形成算法不能很好地跟踪信号统计特征的变化,适应时变环境的能力较差.本文对其进行改进,提出一种实时估计环境噪声及干扰的相关矩阵的方法,使用时变遗忘因子更新相关矩阵,遗忘因子根据目标语音的存在概率变化,最后引入对角加载技术更新滤波器权向量,以保证波束形成的质量.实验结果显示,相比传统的MVDR算法,改进后的MVDR波束形成算法具有更好的降噪效果,能获得更高的分段信噪比和PESQ得分.

Traditional Minimum Variance Distortionless Response(MVDR)beamforming algorithm struggles to accurately track the variations in signal statistical characteristics and exhibits poor adaptability to time-varying environments.In this paper,an enhanced method for real-time estimation of the correlation matrix of environmental noise and interference was proposed.A time-varying forgetting factor was utilized to dynamically update the correlation matrix based on the probability of the presence of the target speech.Finally,diagonal loading technique was introduced to update the filter weight vector to ensure the quality of beamforming.Experimental results demonstrated that,compared to the traditional MVDR algorithm,the improved MVDR beamforming algorithm exhibited superior denoising performance,achieving higher segmental signalto-noise ratios and PESQ scores.