Speaker Identification Based on Classification Sub-space Gaussian Mixture Model

摘要：

This paper proposes a Classification Feature Subspace Gaussian Mixture Model (CGMM), which can improve the training efficiency of conventional Gaussian Mixture Model (GMM) in speaker identification. By taking the advantage of the centralization tendency of similar features in phonetic signals, CGMM uses Vector Quantization (VQ) technique to cluster the similar features into a subspace. In the procedure of training, it establishes a GMM for each sub-space instead of a GMM for all the feature vectors. Our experimental findings show that as the feature vectors were more concentrated in each sub-space, CGMM enhanced the training efficiency and recognition rate of speaker identification as compared with conventional GMM.

关键词： speaker identification VQ (Vector Quantization) feature sub-space classification CGMM (Gaussian Mixture Model)

作者: Wen-wen Xiao Jianbin Zheng Jian Hua Enqi Zhan

作者单位: School of Information Engineering, Wuhan University of Technology, Wuhan, China

会议类型: 国际会议

会议名称: 2011 International Conference on Image Analysis and Signal Processing(2011第三届图像分析与信号处理国际会议 IASP 2011)

会议地点: 武汉

会议语种:英文

页码: 607-611

在线出版日期: 2011-10-21（万方平台首次上网日期，不代表论文的发表时间）