DMCA
Text Independent Speaker Verification Using Adapted Gaussian Mixture Models”, MSc Thesis (2001)
| Venue: | Department of Speech, Music and Hearing |
| Citations: | 3 - 0 self |
BibTeX
@INPROCEEDINGS{Neiberg01textindependent,
author = {Daniel Neiberg and Supervisor H˚akan Melin},
title = {Text Independent Speaker Verification Using Adapted Gaussian Mixture Models”, MSc Thesis},
booktitle = {Department of Speech, Music and Hearing},
year = {2001}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The primary goal of this master thesis project is to implement a text independent speaker verification module for GIVES. Secondary goals are to implement a fast scoring method and compare performance between the implemented text independent module and an available text dependent module. The project also includes a literature study. The text independent module is based on adapted Gaussian Mixture Models and the adaptation equations are derived. Evaluation results show that the text independent module and the text dependent module have almost equal performance on a text dependent recognition task. The results are analyzed and summarized, and improvements are suggested. Unfortunately, the fast scoring method did not work together with all the components in GIVES. Sammanfattning Det primära m˚alet med detta examensarbete är att implementera en textoberoende talarverifieringsmodul för GIVES. Sekundära m˚al är att implementera
Keyphrases
msc thesis text independent module fast scoring method adapted gaussian mixture model detta examensarbete att implementera text dependent recognition task det prim ra alet secondary goal literature study equal performance master thesis project text independent speaker verification module evaluation result available text dependent module al att implementera text dependent module textoberoende talarverifieringsmodul give primary goal adaptation equation implemented text independent module
