Efficient window for monolingual and crosslingual speaker identification using MFCC

In this paper an experimental evaluation of the various windowing techniques using mel-frequency cepstral coefficient (MFCC) for monolingual and crosslingual speaker identification is demonstrated. The set of windows presented here allows a tradeoff between main lobe bandwidth and side lobe ripple d...

Full description

Saved in:
Bibliographic Details
Published in2013 International Conference on Advanced Computing and Communication Systems pp. 1 - 4
Main Authors Nagaraja, B. G., Jayanna, H. S.
Format Conference Proceeding
LanguageEnglish
Japanese
Published IEEE 01.12.2013
Subjects
Communication systems
crosslingual
Frequency-domain analysis
Mel frequency cepstral coefficient
MFCC
monolingual
Speaker identification
Speaker recognition
Speech
Speech recognition
window
Online AccessGet full text
DOI10.1109/ICACCS.2013.6938702

Cover

More Information
Summary:In this paper an experimental evaluation of the various windowing techniques using mel-frequency cepstral coefficient (MFCC) for monolingual and crosslingual speaker identification is demonstrated. The set of windows presented here allows a tradeoff between main lobe bandwidth and side lobe ripple decay. The speaker identification study is conducted using randomly selected 50 speakers from IITG Multi-variability speaker recognition (IITG-MV) database, MFCC feature and Gaussian mixture model (GMM)-universal background model (UBM) classifier. Speaker identification system based on various windowing techniques shown to have considerably improved performance over baseline Hamming window technique.
DOI:10.1109/ICACCS.2013.6938702