Comparison of Generative and Discriminative Approaches for Speaker Recognition with Limited Data
This paper presents a comparison of three different speaker recognition methods deployed in a broadcast news processing system. We focus on how the generative and discriminative nature of these methods affects the speaker recognition framework and we also deal with intersession variability compensat...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Spolecnost pro radioelektronicke inzenyrstvi
2009-09-01
|
Series: | Radioengineering |
Subjects: | |
Online Access: | http://www.radioeng.cz/fulltexts/2009/09_03_307_316.pdf |