Feature extraction in speaker verification under noisy conditions

This thesis describes the development of a robust automatic speaker verification system (ASV) with specific interest in the extraction of dominant acoustic features. Our primary investigation involves the development of robust feature extraction techniques to improve the performance of the system un...

Full description

Saved in:
Bibliographic Details
Main Author: Sirajudeen Gulam Razul.
Other Authors: Kot, Alex Chichung
Format: Theses and Dissertations
Language:English
Published: 2008
Subjects:
Online Access:http://hdl.handle.net/10356/13190
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-13190
record_format dspace
spelling sg-ntu-dr.10356-131902023-07-04T15:52:46Z Feature extraction in speaker verification under noisy conditions Sirajudeen Gulam Razul. Kot, Alex Chichung School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Biometrics This thesis describes the development of a robust automatic speaker verification system (ASV) with specific interest in the extraction of dominant acoustic features. Our primary investigation involves the development of robust feature extraction techniques to improve the performance of the system under noisy conditions. By far, the most widely used feature in this area is the Mel Frequency Cepstral Coefficients (MFCC). The techniques developed here are processing strategies, which improves the MFCC feature set. We have introduced four techniques to improve the robustness of the system against noise, particularly additive white Gaussian noise (AWGN). The first three are integrated processing strategies and the last one a pre-processing technique. These features are subsequently used to train a speaker model which eventually is used to represent a particular speaker. The model that we have selected is the Gaussian Mixture Model (GMM). This model is used as opposed to the Hidden Markov Model (HMM) because of its simplicity and fast processing time. Master of Engineering 2008-07-30T06:06:15Z 2008-10-20T07:18:10Z 2008-07-30T06:06:15Z 2008-10-20T07:18:10Z 1999 1999 Thesis http://hdl.handle.net/10356/13190 en 122 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Biometrics
spellingShingle DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Biometrics
Sirajudeen Gulam Razul.
Feature extraction in speaker verification under noisy conditions
description This thesis describes the development of a robust automatic speaker verification system (ASV) with specific interest in the extraction of dominant acoustic features. Our primary investigation involves the development of robust feature extraction techniques to improve the performance of the system under noisy conditions. By far, the most widely used feature in this area is the Mel Frequency Cepstral Coefficients (MFCC). The techniques developed here are processing strategies, which improves the MFCC feature set. We have introduced four techniques to improve the robustness of the system against noise, particularly additive white Gaussian noise (AWGN). The first three are integrated processing strategies and the last one a pre-processing technique. These features are subsequently used to train a speaker model which eventually is used to represent a particular speaker. The model that we have selected is the Gaussian Mixture Model (GMM). This model is used as opposed to the Hidden Markov Model (HMM) because of its simplicity and fast processing time.
author2 Kot, Alex Chichung
author_facet Kot, Alex Chichung
Sirajudeen Gulam Razul.
format Theses and Dissertations
author Sirajudeen Gulam Razul.
author_sort Sirajudeen Gulam Razul.
title Feature extraction in speaker verification under noisy conditions
title_short Feature extraction in speaker verification under noisy conditions
title_full Feature extraction in speaker verification under noisy conditions
title_fullStr Feature extraction in speaker verification under noisy conditions
title_full_unstemmed Feature extraction in speaker verification under noisy conditions
title_sort feature extraction in speaker verification under noisy conditions
publishDate 2008
url http://hdl.handle.net/10356/13190
_version_ 1772827184910565376