基于自适应超高斯混合模型的语音增强算法

Speech Enhancement Algorithm Based on Adapted Super-Gaussian Mixture Model

语音信号的频谱结构复杂性决定了其短时谱分布不能用单一的概率密度函数(Probability density function,PDF)准确描述。据此,提出了一种采用超高斯混合模型对语音信号幅度谱建模以实现语音增强的新方法。首先,采用超高斯混合模型对语音信号幅度谱的先验分布进行建模,相对于传统的单一模型,该模型能更好地描述语音信号的多类特性;然后,在增强过程中自适应更新混合分量的PDF及其权重,从而克服了传统模型难以跟踪语音信号分布动态变化的缺点。仿真结果表明与传统的短时谱估计算法相比,该算法的噪声抑制性能有较大的提升,增强语音的主观感知质量也有明显改善。

The observation of speech spectral structure shows that the statistics of speech signal cannot be well determined by a simple probability density function （PDF）. Therefore, a speech enhancement algorithm is presented based on the super-Gaussian mixture model. Firstly, the super Gaussian mixture model is employed to model the speech spectral amplitude, which is more flexible in capturing the statistical behavior of speech signals than the conventional simple speech model. Where after, PDF and weight of the mixture components are further adapted, which can overcome the disadvantage that the traditional simple speech model cannot well track the dynamic characteristics of the speech signal. The simulation results show that the proposed algorithm achieves better noise suppression and lower speech distortion compared with the con- ventional short-time spectral estimation algorithms.