基于结构风险最小化准则的高斯混合模型的参数估计  

Structural risk minimization principle based gaussian mixture modeling

作　　者：王立威[1] 王作英[1] 

机构地区：[1]清华大学电子工程系,北京100084

出　　处：《声学学报》2003年第5期403-408,共6页Acta Acustica

摘　　要：隐含马尔可夫模型中,观测向量的概率密度常用高斯混合模型来表示。目前,几乎所有的语音识别系统都是用极大似然准则来估计高斯混合模型的参数。但是,增加模型的成分数,可以使似然度单调上升;另一方面,过分复杂的模型会导致参数训练不充分,对测试集的识别效果反而不好。本文基于统计学习理论中结构风险最小化准则,导出了高斯混合模型的参数估计公式,与基线系统和其它成分数的选择方法相比,有较好的效果。此外根据实际应用时希望模型尽可能简单的原则推广了上述方法。在平均成分数相等的情况下,我们给出的方法比基线系统的误识率有一致的下降。Gaussian mixture model are commonly used as probability density of observed data in Hidden Markov Models. The parameters of the Gaussian mixture model is estimated based on Maximum Likelihood principle in almost all automatic speech recognition systems. However, the value of the likelihood would monotonically increase with the increases of the number of the components. On the other hand, parameters of over-complex model could not be well-trained, and give bad results for testing data. In this paper, we present an estimation of the parameters of Gaussian mixture models based on Structural Risk Minimization principle which is the key principle of statistical learning theory. We further generalized the method for the purpose that simple model is more attractive in real-time systems. The new methodology could reduce the error rate consistently compared with baseline systems which has the same average number of components.

关 键 词：高斯混合模型 参数估计 结构风险最小化准则 统计学习理论 隐含马尔可夫模型 语音信号处理 

分 类 号：O212[理学—概率论与数理统计]