中文摘要：

针对基于梅尔频谱域隐马尔可夫模型（Mel-Frequency Spectral domain Hidden Markov Model,MFS-HMM）的语音增强算法中存在训练集和测试集能量不匹配问题,本文提出了能量匹配的MFS-HMM语音增强方法。该方法采用迭代的期望最大（Expectation Maximization,EM）法在线估计纯净语音和噪声的对数能量调整因子,并在线修正纯净语音和噪声的HMM参数,使得训练集和测试集能量相匹配,有效地解决了能量不匹配对增强语音质量影响的问题。主客观测试结果表明,本文所提方法优于参考算法。

英文摘要：

In order to balance the energy mismatch between the training data and test data in the speech enhancement method based on Mel-Frequency Spectral domain Hidden Markov Model （Mel-Frequency Spectral domain Hidden Markov Mod- el, MFS-HMM）, an energy adjustment method is proposed for MFS-HMM based speech enhancement. In this method, the online estimation of the log-energy adjustment factor for clean speech and noise is obtained by the iterative expectation maxi- mization （EM） method, and the parameters of HMMs of clean speech and noise are modified online, respectively. This makes the energy of training data match to the test data better and the effect of energy mismatch on tho enhanced speech is reduced efficiently. Experimental results of subjective and objective qualities show that, in comparison with the reference methods, the proposed method can get better performance.