线性预报误差时变方差补偿与语音增强

Time-varying variance compensating of the linear prediction error for speech enhancement

对常规的语音信号线性预报模型进行了推广 ,将线性预报误差方差考虑为时变的 ,这在一定程度上可对语音信号帧内非平稳特性进行补偿。基于对线性预报残差的短时 (2ms～ 4ms)特性分析 ,给出了线性预报系数及线性预报误差时变方差的迭代估计方法。将此模型应用于基于Kalman滤波的语音增强方法。仿真结果表明 。

The linear prediction (LP) model with time-varying variance of the prediction error is proposed for speech signal modeling. An iterative parameter estimation method is then presented based on the analysis of the short segment (2 ms～4 ms) of LP residual. This approach is used in the framework of speech enhancement based on Kalman filter. A comparative study with existing methods is proposed and shows that the adopted model provides a higher improvement of signal to noise ratio (SNR) than the ordinary LP model.