基于GMM-UBM的说话人确认系统的研究

Research on Speaker Identifying System Based on GMM-UBM

在基于GMM的说话人确认系统中,模型的训练是为每个说话人的语音建立模型,然后通过一定的算法找到一组参数?,使似然概率最大。文中通过对GMM的研究提出一种改进的模糊C均值算法(FCM)并将改进后的算法应用到模型初始化中。同时,GMM在话者确认时,语音数据不足会导致识别率下降,本文采用能覆盖话者语音的高斯混合模型-通用背景模型(GMM-UBM)作为识别模型,通过算法比较及实验分析可知,改进算法后的系统在识别率上明显优于传统的基于GMM的说话人识别系统。

In speaker recognition system based on GMM, model training was to build probability model for each speaker, then a set of parameters 2 was found with a certain algorithm and which made likelihood probability maximum. After the GMM was studied, the improved Fuzzy C Means algorithm （FCM） was proposed and introduced to model initialization. In GMM speaker recognition, speech data deficiency can lead to recognition rate to be lower, so the GMM-UBM was used as the recognition model. Through algorithms comparasion and test analyses, the experimental results show that the recognition rate of the improved algorithm is obviously superior to the traditional speaker recognition system based on GMM,