Secure Random 2D Subspace Techniques In GMM Based Speaker Verification System
Several subspace methods are studied in Gaussian Mixture Model (GMM) based speaker verification. The objective is to reduce the dimension of feature set while retaining the prominent spectral features that can uniquely represent a user .
Saved in:
Main Author: | Chong, Lee Ying |
---|---|
Format: | Thesis |
Published: |
2008
|
Subjects: | |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Subspace Approach For Speech Signal Modelling And Classification
by: Tan, Alan Wee Chiat
Published: (2007) -
Private Biometrics Realisation Through Iris Verification
by: Chong, Siew Chin
Published: (2005) -
Functional Verification Test Time Reduction Through Behavioral Functional Model
by: Lee , Chee Keng
Published: (2014) -
Reissuable Biometrics Through Offline Handwritten Signature Verification
by: Ooi, Shih Yin
Published: (2008) -
Single-Sensor Hand Geometry And Palmprint Verification System
by: Goh, Michael Kah Ong
Published: (2004)