GMM文本无关的说话人识别系统研究

Research on GMM text-independent speaker recognition

在高斯混合模型(Gaussian Mixture Model,GMM)训练时,对传统的模型参数初始化方法(随机法、K均值聚类法)进行改进,提出分裂法与K均值聚类相结合的新方法。实验表明,采用改进的方法与传统方法相比,系统平均识别率有15.47%和7.5%的提高。研究了GMM的阶数、协方差阈值、预加重系数对系统识别率的影响。对实验结果进行详细分析,并根据实验数据,取它们各自表现最好的值,从而使构建的说话人识别系统获得一个较高的识别率。实验表明,在规定的实验条件下,系统可达到90%以上的识别率。

This paper improves the traditional method of Gaussian Mixture Mode（lGMM） parameters initialization at the time of GMM training.A new approach which combines division and K-means clustering is presented.The experiment shows that the proposed method can achieve the average recognition rate increase by 15.47% and 7.5% compared with the randomization and Kmeans clustering.At the same time,the impact of the order of GMM,covariance threshold and pre-emphasis coefficient on system recognition rate are studied.Meanwhile,the experiment results are analyzed in detail.In order to make the speaker recognition system get a higher recognition rate,their optimal values are chosen from the experiment data.The experiment shows that the system can achieve the recognition rate with above 90% under the provided experimental condition.