Analysis of the Hilbert Spectrum for Text-Dependent Speaker Verification

•Seven different features are obtained from the instantaneous frequencies and energies of the IMFs, obtained using MEMD.•The seven features are useful at very low dimensions (

Saved in:
Bibliographic Details
Published in:Speech communication 2018-02, Vol.96, p.207-224
Main Authors: Sharma, Rajib, Bhukya, Ramesh K., Prasanna, S.R.M.
Format: Article
Language:English
Subjects:
Background noise
Data analysis
Empirical analysis
Feature extraction
IMFs
MEMD
MFCCs
Noise
Nonlinear analysis
Speech
TDSV
Voice recognition
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Seven different features are obtained from the instantaneous frequencies and energies of the IMFs, obtained using MEMD.•The seven features are useful at very low dimensions (
ISSN:0167-6393
1872-7182
DOI:10.1016/j.specom.2017.12.001