# Kernel Combination for SVM Speaker Verification

## Abstract

We present a new approach for constructing the kernels used to build support vector machines for speaker verification. The idea is to construct new kernels by taking linear combination of many kernels such as the GLDS and GMM supervector kernels. In this new kernel combination, the combination weights are speaker dependent rather than universal weights on score level fusion and there is no need for extra-data to estimate them. An experiment on the NIST 2006 speaker recognition evaluation dataset (all trial) was done using three different kernel functions (GLDS kernel, linear and Gaussian GMM supervector kernels). We compared our kernel combination to the optimal linear score fusion obtained using logistic regression. This optimal score fusion was trained on the same test data. We had an equal error rate of ${\displaystyle \simeq 5,9\%}$ using the kernel combination technique which is better than the optimal score fusion system (${\displaystyle \simeq 6,0\%}$).

## Bibtex (lrde.bib)

```@InProceedings{	  dehak.08.odysseya,
author	= {R\'eda Dehak and Najim Dehak and Patrick Kenny and Pierre
Dumouchel},
title		= {Kernel Combination for {SVM} Speaker Verification},
booktitle	= {Proceedings of the Speaker and Language Recognition
Workshop (IEEE-Odyssey 2008)},
year		= 2008,
month		= jan,
abstract	= {We present a new approach for constructing the kernels
used to build support vector machines for speaker
verification. The idea is to construct new kernels by
taking linear combination of many kernels such as the GLDS
and GMM supervector kernels. In this new kernel
combination, the combination weights are speaker dependent
rather than universal weights on score level fusion and
there is no need for extra-data to estimate them. An
experiment on the NIST 2006 speaker recognition evaluation
dataset (all trial) was done using three different kernel
functions (GLDS kernel, linear and Gaussian GMM supervector
kernels). We compared our kernel combination to the optimal
linear score fusion obtained using logistic regression.
This optimal score fusion was trained on the same test
data. We had an equal error rate of \$\simeq 5,9\%\$ using
the kernel combination technique which is better than the
optimal score fusion system (\$\simeq 6,0\%\$).}
}```