摘要
为了提高基于G auss混合模型通用背景模型(GMM-U BM)的说话人辨认系统的运算效率,提出一种基于树的核心挑选算法(TBK S),通过将U BM中的各个G auss分布按组织成树形结构,来减少从中挑选核心分布的运算量。实验结果表明:对1 000个说话人进行辨认,TBK S与现有的基于特征矢量重排序的剪枝算法(ORBP)相结合,将基于GMM-U BM的辨认系统的运算速度提高21.9倍,误识率却只上升不到4%;TBK S和ORBP相结合,可大幅度提高GMM-U BM系统的运算效率,而基本不降低识别率。
A tree-based kernel selection （TBKS） algorithm, in which all the Gaussian components in the universal background model are clustered hierarchically into a tree structure for efficient kernel selection, was developed as a computationally efficient approach for Gaussian mixture model-universal background model- based speaker identification. In tests on a database of 1 000 speakers, integration of the TBKS algorithm and an observation reordering-based pruning （ORBP） method improved the computation speed by a factor of 21.9 with only 4% increase in error rate compared with the baseline GMM-UBM system. The experimental results show that by integrating the TBKS and ORBP algorithms, the eomputation efficiency of the GMM-UBM system can be significantly improved with almost no reduetion in recognition rate.
出处
《清华大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2006年第7期1305-1308,共4页
Journal of Tsinghua University(Science and Technology)
关键词
信息处理
说话人辨认
Gauss混合模型
通用背景模型
基于树的核心挑选
information processing
speaker identification
Gaussian mixture model
universal background model
tree-based kernel selection
