SVM based Speaker Verification and gender dependent NAP variability compensation
In recent years, Support Vector Machine is used in many application areas and has shown dramatic achievement. In this paper, we apply it to a text-independent speaker verification task using the NIST 2001 Speaker Recognition database. Starting from a baseline based on Gaussian mixture models, we use the state-of-the-art GMM supervector and SVM to improve the performance. We alter several kernels and find out the linear kernel yields the best performance. Finally, the latest compensation method nuisance attribute projection (NAP) is examined, and the gender-dependent NAP shows more reduction than gender-independent NAP in equal error rate.
speaker verification UBM-GMM support vector machine nuisance attribute projection
Jianshu Chao Wei Huang Yaxin Zhang
College of Life Science and Biotechnology Shanghai Jiao Tong University Shanghai, China Motorola China Research Center Motorola (China) Electronics Ltd. Shanghai, China
国际会议
上海
英文
710-713
2008-05-16（万方平台首次上网日期，不代表论文的发表时间）