Development of a voice activity controlled noise canceller

Ali O. Abid Noor, Salina Abdul Samad, Aini Hussain

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In this paper, a variable threshold voice activity detector (VAD) is developed to control the operation of a two-sensor adaptive noise canceller (ANC). The VAD prohibits the reference input of the ANC from containing some strength of actual speech signal during adaptation periods. The novelty of this approach resides in using the residual output from the noise canceller to control the decisions made by the VAD. Thresholds of full-band energy and zero-crossing features are adjusted according to the residual output of the adaptive filter. Performance evaluation of the proposed approach is quoted in terms of signal to noise ratio improvements as well mean square error (MSE) convergence of the ANC. The new approach showed an improved noise cancellation performance when tested under several types of environmental noise. Furthermore, the computational power of the adaptive process is reduced since the output of the adaptive filter is efficiently calculated only during non-speech periods.

Original languageEnglish
Pages (from-to)6727-6745
Number of pages19
JournalSensors (Switzerland)
Volume12
Issue number5
DOIs
Publication statusPublished - May 2012

Fingerprint

Noise
Adaptive filters
Detectors
adaptive filters
output
detectors
Mean square error
Band structure
Signal to noise ratio
roots of equations
thresholds
Signal-To-Noise Ratio
cancellation
energy bands
Sensors
signal to noise ratios
evaluation
sensors

Keywords

  • Adaptive noise canceller
  • Threshold adjustment
  • Voice activity detector

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Atomic and Molecular Physics, and Optics
  • Analytical Chemistry
  • Biochemistry

Cite this

Development of a voice activity controlled noise canceller. / Abid Noor, Ali O.; Abdul Samad, Salina; Hussain, Aini.

In: Sensors (Switzerland), Vol. 12, No. 5, 05.2012, p. 6727-6745.

Research output: Contribution to journalArticle

@article{a4b6a8262da34c19b777e75ca4107a3c,
title = "Development of a voice activity controlled noise canceller",
abstract = "In this paper, a variable threshold voice activity detector (VAD) is developed to control the operation of a two-sensor adaptive noise canceller (ANC). The VAD prohibits the reference input of the ANC from containing some strength of actual speech signal during adaptation periods. The novelty of this approach resides in using the residual output from the noise canceller to control the decisions made by the VAD. Thresholds of full-band energy and zero-crossing features are adjusted according to the residual output of the adaptive filter. Performance evaluation of the proposed approach is quoted in terms of signal to noise ratio improvements as well mean square error (MSE) convergence of the ANC. The new approach showed an improved noise cancellation performance when tested under several types of environmental noise. Furthermore, the computational power of the adaptive process is reduced since the output of the adaptive filter is efficiently calculated only during non-speech periods.",
keywords = "Adaptive noise canceller, Threshold adjustment, Voice activity detector",
author = "{Abid Noor}, {Ali O.} and {Abdul Samad}, Salina and Aini Hussain",
year = "2012",
month = "5",
doi = "10.3390/s120506727",
language = "English",
volume = "12",
pages = "6727--6745",
journal = "Sensors (Switzerland)",
issn = "1424-8220",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "5",

}

TY - JOUR

T1 - Development of a voice activity controlled noise canceller

AU - Abid Noor, Ali O.

AU - Abdul Samad, Salina

AU - Hussain, Aini

PY - 2012/5

Y1 - 2012/5

N2 - In this paper, a variable threshold voice activity detector (VAD) is developed to control the operation of a two-sensor adaptive noise canceller (ANC). The VAD prohibits the reference input of the ANC from containing some strength of actual speech signal during adaptation periods. The novelty of this approach resides in using the residual output from the noise canceller to control the decisions made by the VAD. Thresholds of full-band energy and zero-crossing features are adjusted according to the residual output of the adaptive filter. Performance evaluation of the proposed approach is quoted in terms of signal to noise ratio improvements as well mean square error (MSE) convergence of the ANC. The new approach showed an improved noise cancellation performance when tested under several types of environmental noise. Furthermore, the computational power of the adaptive process is reduced since the output of the adaptive filter is efficiently calculated only during non-speech periods.

AB - In this paper, a variable threshold voice activity detector (VAD) is developed to control the operation of a two-sensor adaptive noise canceller (ANC). The VAD prohibits the reference input of the ANC from containing some strength of actual speech signal during adaptation periods. The novelty of this approach resides in using the residual output from the noise canceller to control the decisions made by the VAD. Thresholds of full-band energy and zero-crossing features are adjusted according to the residual output of the adaptive filter. Performance evaluation of the proposed approach is quoted in terms of signal to noise ratio improvements as well mean square error (MSE) convergence of the ANC. The new approach showed an improved noise cancellation performance when tested under several types of environmental noise. Furthermore, the computational power of the adaptive process is reduced since the output of the adaptive filter is efficiently calculated only during non-speech periods.

KW - Adaptive noise canceller

KW - Threshold adjustment

KW - Voice activity detector

UR - http://www.scopus.com/inward/record.url?scp=84861537863&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861537863&partnerID=8YFLogxK

U2 - 10.3390/s120506727

DO - 10.3390/s120506727

M3 - Article

VL - 12

SP - 6727

EP - 6745

JO - Sensors (Switzerland)

JF - Sensors (Switzerland)

SN - 1424-8220

IS - 5

ER -