基于概率模型和倒谱差分的特征补偿算法

Feature Compensation Method Based on Probability Model and Spectrum Difference

在概率模型中,给出了引入倒谱预测值的动态相关性来进行特征补偿的方法。该方法采用期望最大化(EM)算法来估计联合分布参数,基于语音和噪声的先验概率密度,在倒谱域中对语音特征参数进行最小均方误差预测(MMSE),以提高语音识别精度。不同噪声环境和不同信噪比下的实验结果表明,该方法能有效地提高噪声环境下的中文连续语音识别的正确率。

The paper introduces a new feature compensation method which will induct the relativity of the prediction of spectrum based probability model in detail. The method evaluates the parameters of the joint distribution using the expectation maximizaton （EM） algorithm. The minimum mean squared error （MMSE） estimator for the speech feature parameters in spectrum-domain based the prior probability distribution is to enhance the correctness of speech recognition. The algorithm is tested in different poise and signal noise ratio （SNR）. Subjective measure testifies that this method can increase the correctness of continuous speech recognition.