Enhancing speaker verification in noisy environments using Recursive Least-Squares (RLS) adaptive filter

Mohd Zaizu Ilyas, Salina Abdul Samad, Aini Hussain, Khairul Anuar Ishak

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

1 Citation (Scopus)

Abstract

In this paper, we present a speaker verification system based on the Hidden Markov Model (HMM) technique and Recursive Least Squares (RLS) adaptive filtering. The aim of using RLS adaptive filtering is to improve the HMM performance in noisy environments. A Malay spoken digit database is used for the testing and validation modules. It is shown that, in a clean environment a total success rate (TSR) of 89.97% is achieved using HMM. For speaker verification, the true speaker rejection rate is 25.3% while the impostor acceptance rate is 9.99% and the equal error rate (EER) is 16.66%. In noisy environments without RLS adaptive filtering TSRs of between 43.07%-51.26% are achieved for SNRs of 0-30 dBs. Meanwhile, after RLS filtering, TSRs of between 50.95%-56.75% are achieved for SNRs 0-30 dB.

Original languageEnglish
Title of host publicationProceedings - International Symposium on Information Technology 2008, ITSim
Volume3
DOIs
Publication statusPublished - 2008
EventInternational Symposium on Information Technology 2008, ITSim - Kuala Lumpur
Duration: 26 Aug 200829 Aug 2008

Other

OtherInternational Symposium on Information Technology 2008, ITSim
CityKuala Lumpur
Period26/8/0829/8/08

Fingerprint

Adaptive filtering
Adaptive filters
Hidden Markov models
Testing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Ilyas, M. Z., Abdul Samad, S., Hussain, A., & Ishak, K. A. (2008). Enhancing speaker verification in noisy environments using Recursive Least-Squares (RLS) adaptive filter. In Proceedings - International Symposium on Information Technology 2008, ITSim (Vol. 3). [4631877] https://doi.org/10.1109/ITSIM.2008.4631877

Enhancing speaker verification in noisy environments using Recursive Least-Squares (RLS) adaptive filter. / Ilyas, Mohd Zaizu; Abdul Samad, Salina; Hussain, Aini; Ishak, Khairul Anuar.

Proceedings - International Symposium on Information Technology 2008, ITSim. Vol. 3 2008. 4631877.

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

Ilyas, MZ, Abdul Samad, S, Hussain, A & Ishak, KA 2008, Enhancing speaker verification in noisy environments using Recursive Least-Squares (RLS) adaptive filter. in Proceedings - International Symposium on Information Technology 2008, ITSim. vol. 3, 4631877, International Symposium on Information Technology 2008, ITSim, Kuala Lumpur, 26/8/08. https://doi.org/10.1109/ITSIM.2008.4631877
Ilyas MZ, Abdul Samad S, Hussain A, Ishak KA. Enhancing speaker verification in noisy environments using Recursive Least-Squares (RLS) adaptive filter. In Proceedings - International Symposium on Information Technology 2008, ITSim. Vol. 3. 2008. 4631877 https://doi.org/10.1109/ITSIM.2008.4631877
Ilyas, Mohd Zaizu ; Abdul Samad, Salina ; Hussain, Aini ; Ishak, Khairul Anuar. / Enhancing speaker verification in noisy environments using Recursive Least-Squares (RLS) adaptive filter. Proceedings - International Symposium on Information Technology 2008, ITSim. Vol. 3 2008.
@inproceedings{7f4624d3aa7a40b3a6ef3487b4f11634,
title = "Enhancing speaker verification in noisy environments using Recursive Least-Squares (RLS) adaptive filter",
abstract = "In this paper, we present a speaker verification system based on the Hidden Markov Model (HMM) technique and Recursive Least Squares (RLS) adaptive filtering. The aim of using RLS adaptive filtering is to improve the HMM performance in noisy environments. A Malay spoken digit database is used for the testing and validation modules. It is shown that, in a clean environment a total success rate (TSR) of 89.97{\%} is achieved using HMM. For speaker verification, the true speaker rejection rate is 25.3{\%} while the impostor acceptance rate is 9.99{\%} and the equal error rate (EER) is 16.66{\%}. In noisy environments without RLS adaptive filtering TSRs of between 43.07{\%}-51.26{\%} are achieved for SNRs of 0-30 dBs. Meanwhile, after RLS filtering, TSRs of between 50.95{\%}-56.75{\%} are achieved for SNRs 0-30 dB.",
author = "Ilyas, {Mohd Zaizu} and {Abdul Samad}, Salina and Aini Hussain and Ishak, {Khairul Anuar}",
year = "2008",
doi = "10.1109/ITSIM.2008.4631877",
language = "English",
isbn = "9781424423286",
volume = "3",
booktitle = "Proceedings - International Symposium on Information Technology 2008, ITSim",

}

TY - GEN

T1 - Enhancing speaker verification in noisy environments using Recursive Least-Squares (RLS) adaptive filter

AU - Ilyas, Mohd Zaizu

AU - Abdul Samad, Salina

AU - Hussain, Aini

AU - Ishak, Khairul Anuar

PY - 2008

Y1 - 2008

N2 - In this paper, we present a speaker verification system based on the Hidden Markov Model (HMM) technique and Recursive Least Squares (RLS) adaptive filtering. The aim of using RLS adaptive filtering is to improve the HMM performance in noisy environments. A Malay spoken digit database is used for the testing and validation modules. It is shown that, in a clean environment a total success rate (TSR) of 89.97% is achieved using HMM. For speaker verification, the true speaker rejection rate is 25.3% while the impostor acceptance rate is 9.99% and the equal error rate (EER) is 16.66%. In noisy environments without RLS adaptive filtering TSRs of between 43.07%-51.26% are achieved for SNRs of 0-30 dBs. Meanwhile, after RLS filtering, TSRs of between 50.95%-56.75% are achieved for SNRs 0-30 dB.

AB - In this paper, we present a speaker verification system based on the Hidden Markov Model (HMM) technique and Recursive Least Squares (RLS) adaptive filtering. The aim of using RLS adaptive filtering is to improve the HMM performance in noisy environments. A Malay spoken digit database is used for the testing and validation modules. It is shown that, in a clean environment a total success rate (TSR) of 89.97% is achieved using HMM. For speaker verification, the true speaker rejection rate is 25.3% while the impostor acceptance rate is 9.99% and the equal error rate (EER) is 16.66%. In noisy environments without RLS adaptive filtering TSRs of between 43.07%-51.26% are achieved for SNRs of 0-30 dBs. Meanwhile, after RLS filtering, TSRs of between 50.95%-56.75% are achieved for SNRs 0-30 dB.

UR - http://www.scopus.com/inward/record.url?scp=57349156721&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57349156721&partnerID=8YFLogxK

U2 - 10.1109/ITSIM.2008.4631877

DO - 10.1109/ITSIM.2008.4631877

M3 - Conference contribution

AN - SCOPUS:57349156721

SN - 9781424423286

VL - 3

BT - Proceedings - International Symposium on Information Technology 2008, ITSim

ER -