一种改进的LSA语音增强算法

针对说话人识别的噪声鲁棒性问题,在对数谱最小均方差误差估计算法基础上,采用改进的最小值控制递归平均算法对语音帧信噪比进行估计,通过对前一帧的短时功率谱进行2次平滑和前向多帧最小值搜索,结合语音存在概率估计出当前帧的信噪比,并根据信噪比自适应调整增益因子的大小,对噪声进行消除。构建了一种改进的LSA语音增强方法,使用该方法可以使增强后的语音保持较高的自然度。实验结果表明,与MMSE-LSA算法比较,改进的LSA算法具有更好的语音增强效果,在5dB各类噪声环境下,其平均信噪比较MMSE-LSA算法提高1.36dB,主观语音质量评估平均提高8%。将该方法用于说话人识别系统,其检测代价较采用MMSE-LSA算法的系统平均降低3%。

Improved LSA speech enhancement algorithm

An improved ln-spectral amplitude (LSA) speech enhancement method was proposed for robust speaker recognition. The LSA feature preserves the naturalness of speech and hence is more suitable for speaker recognition. However, the traditional minimum mean square error-ln-spectral amplitude(MMSE-LSA) method cannot adjust the gain factor according to input signal to noise ratio (SNR), thus often resulting in performance degradation when SNR is low.A recursive averaging algorithm was proposed for estimating SNR of speech frame efficiently, thereby affording adaptive gain control of the speech enhancement system. The improved LSA speech enhancement method can output high fidelity speech signal and minimize the impact on the naturalness of speech signal. Experimental results show that under 5 dB noise,SNR of the new method's output is 1.36 dB better than that of the traditional MMSE-LSA, and perceptual evaluation of speech quality(PESQ) score rises 0.08 on average. The method is also applied to speaker recognition system and the detection cost score is about 3% lower than that of MMSE-LSA.