基于SVM—GMM混合模型说话人辨认的研究

建立一种新的混合模型-SVM-GMM模型，用以提高说话人辨认的识别率。阐述高斯混合模型（GMM）和支持向量机（SVM）建立的基本原理，分别指出高斯混合模型和支持向量机在实际应用中的不足之处，并针对两种模型的特点，提出将GMM模型的输出机制引入到SVM模型中，以便于调整支持向量（SVM）模型的概率输出，并建立SVM-GMM混合模型。通过实验对比，验证使用SVM-GMM模型能有效地提高系统识别率。

Research of the speaker verification based on the SVM-GMM mixed model

We put forward a new SVM-GMM mixture model to improve recognition rate of the speaker verification system in the paper. Support vector machines （SVM） and Gaussian mixture model （GMM） are widely applied to the speaker verification, but they both have the disadvantages. We present a new approach for speaker verification based on their feature. The new model introduces the output of the Gaussian mixture model to Support vector machines, in Order to adjust the probabilistie output of the support vector of machines. It can compliment support vector machines with probabilistic information. The experiments have proved that SVM-GMM mixture model can effectively enhance the recognition rate of the speaker verification system.