Multimodal biometrics using multiple feature representations to speaker identification system

Rami Al-Hmouz, Khaled Daqrouq, Ali Morfeq, Witold Pedrycz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Multimodal biometrics combines information coming from multiple biometrics with a key objective to reduce the limitations associated with any single biometric method such as low accuracy, limited security, noisy measurements, etc. In this study, different multimodal speaker identification approaches are investigated. Linear predictive coding features, Mel-frequency cepstral coefficients features, discrete wavelet based linear predictive coding features are examined with the use of different combinations of features applied to the identification system. In building the multimodal system, fusion is realized at the score level using Gaussian mixture model. The system is tested on publicly available data set and shows improvement in the classification rate for all feature extraction methods.

Original languageEnglish
Title of host publication2015 International Conference on Information and Communication Technology Research, ICTRC 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages314-317
Number of pages4
ISBN (Electronic)9781479989669
DOIs
Publication statusPublished - Jul 14 2015
Event1st International Conference on Information and Communication Technology Research, ICTRC 2015 - Abu Dhabi, United Arab Emirates
Duration: May 17 2015May 19 2015

Publication series

Name2015 International Conference on Information and Communication Technology Research, ICTRC 2015

Other

Other1st International Conference on Information and Communication Technology Research, ICTRC 2015
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period5/17/155/19/15

Keywords

  • DWLPC
  • LPC
  • MFCC
  • Multimodal biometrics
  • speaker identification

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Multimodal biometrics using multiple feature representations to speaker identification system'. Together they form a unique fingerprint.

Cite this