A new score normalizaion algorithm based on EMD-Tnorm for speaker verification

Li Yanping1,2、Ding Hui2,3、Tang Zhenmin2

Strategic Study of CAE ›› 2010, Vol. 12 ›› Issue (2) : 95-100.

PDF(722 KB)
PDF(722 KB)
Strategic Study of CAE ›› 2010, Vol. 12 ›› Issue (2) : 95-100.

A new score normalizaion algorithm based on EMD-Tnorm for speaker verification

  • Li Yanping1,2、Ding Hui2,3、Tang Zhenmin2

Author information +
History +

Abstract

In this paper, the verification system from two aspects was improved. On one hand, we extended MixMax model that the EMD (earth mover's distance) can be applied, which can remove the disturbance of noise; on the other hand, we improved the Tnorm score normalization method based on the EMD. Experimental results show that this method can compensate the speaker-dependent and test-dependent variability, also show a stable performance improvement by decreasing the FA and FR.

Keywords

speaker verification / robustness / earth mover’s distance / MixMax model

Cite this article

Download citation ▾
Li Yanping,Ding Hui,Tang Zhenmin. A new score normalizaion algorithm based on EMD-Tnorm for speaker verification. Strategic Study of CAE, 2010, 12(2): 95‒100
AI Summary AI Mindmap
PDF(722 KB)

Accesses

Citations

Detail

Sections
Recommended

/