A Study on Improvements of Noise Rebustness for HMM-based Speech Recognition

为了实现鲁棒的连续密度隐马尔可夫模型用于噪声语音识别，本文基于人的听觉特征，开发了一种对高信噪比频率区域形成峰敏感的频率加权隐马尔可夫模型。该隐马尔可夫模型将高斯概率密度函数的协方差矩阵固定为频率加权矩阵的逆矩阵，以利用群延迟谱的鲁棒性，并将其在频域的相对感知重要性纳入隐马尔可夫模型。利用NOISEX-92国际数据库，研究了几种频率加权函数和频率加权矩阵的标度方法。单词识别测试的结果总结如下。(1)由每个均值向量得到的平滑功率谱给出了最鲁棒的HMM。(2)将权重矩阵转换为协方差矩阵的最佳尺度是权重系数和等于1或转换协方差的行列式比初始hmm的行列式大50 ~ 150倍。(3)频率加权HMM的鲁棒性需要更大的状态数。(4)自适应预强调提高了对高频区域能量较低噪声的鲁棒性。(5)对于白色、粉红色和汽车噪声，频率加权HMM比标准对角线HMM获得6至12 dB的信噪比增益。(6)即使采用标准的谱减法降噪方法对含噪语音进行预处理，频率加权HMM在极低信噪比条件下的识别分数也比传统HMM高10%左右。

In order to realize robust continuous density Hidden Markov Models (HMM) for noisy speech recognition, this study develops a frequency-weighted HMM based on the human auditory characteristics which is seseitive to formant peaks in high SNR frequency region. In this HMM,the covariance matrices of Gaussian probability density functions are fixed to the inverse of frequency weighting matrices in order to utilize the robustness of group delay spectra and also to incorporate their relative perceptual importance in frequency domain into HMM.Several frequency weighting functions and the scaling methods of frequency weighting matrices are examined using the international data base of NOISEX-92. The results of word recognition tests are summarized as follows.(1) The smoothed power spectrum derived from each mean vector gives the most robust HMM.(2) The optimum scaling to convert the weighting matrices to the covariance matrices is such that the sum of weighting coefficients is equal to one or the determinants of the converted covariances are 50 to 150 times larger than those of initial HMMs.(3) A larger number of states is required to attain the robustness in the frequency-weighted HMM.(4) Adaptive preemphasis improves the robustness to noises which have less energy in the high frequency region.(5) The frequency-weighted HMM attains SNR gains of 6 to 12 dB over a standard diagonal HMM for white, pink, and car noises.(6) Even when preprocessing the noisy speech by the standard noise reduction method of spectral subtraction, the frequency weighted HMM attains about 10% higher recognition scores in very low SNR condition than the conventional HMM.