|
KMID : 0917520020090020135
|
|
Journal of Speech Sciences
2002 Volume.9 No. 2 p.135 ~ p.146
|
|
|
A Study on Background Speaker Selection Method in Speaker Verification System
|
|
|
|
|
Abstract
|
|
|
Generally a speaker verification system improves its system recognition ratio by fregularizing log likelihood ratio, using a pseaker model and its background speaker model that are required to be verified. The speaker-based cohort method is one of the methods that are widely used for selecting background speaker model. Recently, Gaussian-based cohort model has been suggested as a virtually synthesized cohort model, and unlike a speaker-based model, this is the method that chooses only the probability distributions close to basic speaker´s probability distribution among the several negihboring speakers´ probability distributions and thereby synthesizes a new virtual speaker model. It shows more excellent results than the existing speaker-based method.
This study compared the existing speaker-based background speaker models and virtual speaker models and then constructed new virtual background speaker model groups which combined them in a certain ratio. For this, this study constructed a speaker verification system that uses GMM (Gaussin Mixture Model), and foudn that the suggested method of selecting vitrual background speaker model shows more improved performance.
|
|
|
KEYWORD
|
|
|
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|
|