A NOVEL SPEAKER CLUSTERING ALGORITHM IN SPEAKER RECOGNITION SYSTEM

摘要：

Speaker clustering is involved in Serial structure speaker identification system to reduce the algorithm delay and computational complexity. The speech is first classified into speaker group, and then searches the most likely one inside the group. Difference between Gaussian Mixture Models (GMMs) is widely applied in speaker classification. The paper proposes a novel measure based on pseudo-divergence, the ratio of Inter-Model dispersion to Intra-Model dispersion, to denote the difference between GMMs. And the measure is used to perform speaker clustering. Experiments indicate that the measurement works well to denote the difference of GMMs and has improved performance of speaker clustering.

关键词： Speaker clustering speaker recognition Gaussian Mixture Model pseudo-divergence

作者: BO WANG JING ZHAO XUAN PENG BI-CHENG LI

作者单位: National Digital Switching System Engineering and Technology Research Center, Zhengzhou 450002, China

会议类型: 国际会议

会议名称: 2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)

会议地点: 大连

会议语种:英文

页码: 3298-3302

在线出版日期: 2006-08-13（万方平台首次上网日期，不代表论文的发表时间）