Noise cancellation using selectable adaptive algorithm for speech in variable noise environment

Roshahliza M. Ramli, Ali O.Abid Noor, Salina Abdul Samad

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Some of the teething problems associated in the use of two-sensor noise cancellation systems are the nature of the noise signals—a problem that imposes the use of highly complex algorithms in reducing the noise. The usage of such methods can be impractical for many real time applications, where speed of convergence and processing time are critical. At the same time, the existing approaches are based on using a single, often complex adaptive filter to minimize noise, which has been determined to be inadequate and ineffective. In this paper, a new mechanism is proposed to reduce background noise from speech communications. The procedure is based on a two-sensor adaptive noise canceller that is capable of assigning an appropriate filter adapting to properties of the noise. The criterion to achieve this is based on measuring the eigenvalue spread based on the autocorrelation of the input noise. The proposed noise canceller (INC) applies an adaptive algorithm according to the characteristics of the input signal. Various experiments based on this technique using real-world signals are conducted to gauge the effectiveness of the approach. Initial results illustrated the system capabilities in executing noise cancellation under different types of environmental noise. The results based on the INC technique indicate fast convergence rates; improvements up to 30 dB in signal-to-noise ratio and at the same time shows 65% reduction of computational power compared to conventional method.

Original languageEnglish
Pages (from-to)1-8
Number of pages8
JournalInternational Journal of Speech Technology
DOIs
Publication statusAccepted/In press - 3 Jun 2017

Fingerprint

Adaptive algorithms
Speech communication
Sensors
Adaptive filters
Autocorrelation
Gages
Signal to noise ratio
Processing
Experiments
Sensor
Filter
communications
Real World
Speech Communication
Computational
Conventional
Signal-to-noise Ratio
Experiment
experiment

Keywords

  • Adaptive algorithms
  • Adaptive filtering
  • Eigenvalue spread
  • Environmental noise
  • Noise cancellation

ASJC Scopus subject areas

  • Software
  • Language and Linguistics
  • Human-Computer Interaction
  • Linguistics and Language
  • Computer Vision and Pattern Recognition

Cite this

Noise cancellation using selectable adaptive algorithm for speech in variable noise environment. / Ramli, Roshahliza M.; Noor, Ali O.Abid; Abdul Samad, Salina.

In: International Journal of Speech Technology, 03.06.2017, p. 1-8.

Research output: Contribution to journalArticle

@article{7a7d83523d434158a8985c23dc169798,
title = "Noise cancellation using selectable adaptive algorithm for speech in variable noise environment",
abstract = "Some of the teething problems associated in the use of two-sensor noise cancellation systems are the nature of the noise signals—a problem that imposes the use of highly complex algorithms in reducing the noise. The usage of such methods can be impractical for many real time applications, where speed of convergence and processing time are critical. At the same time, the existing approaches are based on using a single, often complex adaptive filter to minimize noise, which has been determined to be inadequate and ineffective. In this paper, a new mechanism is proposed to reduce background noise from speech communications. The procedure is based on a two-sensor adaptive noise canceller that is capable of assigning an appropriate filter adapting to properties of the noise. The criterion to achieve this is based on measuring the eigenvalue spread based on the autocorrelation of the input noise. The proposed noise canceller (INC) applies an adaptive algorithm according to the characteristics of the input signal. Various experiments based on this technique using real-world signals are conducted to gauge the effectiveness of the approach. Initial results illustrated the system capabilities in executing noise cancellation under different types of environmental noise. The results based on the INC technique indicate fast convergence rates; improvements up to 30 dB in signal-to-noise ratio and at the same time shows 65{\%} reduction of computational power compared to conventional method.",
keywords = "Adaptive algorithms, Adaptive filtering, Eigenvalue spread, Environmental noise, Noise cancellation",
author = "Ramli, {Roshahliza M.} and Noor, {Ali O.Abid} and {Abdul Samad}, Salina",
year = "2017",
month = "6",
day = "3",
doi = "10.1007/s10772-017-9425-1",
language = "English",
pages = "1--8",
journal = "International Journal of Speech Technology",
issn = "1381-2416",
publisher = "Springer Netherlands",

}

TY - JOUR

T1 - Noise cancellation using selectable adaptive algorithm for speech in variable noise environment

AU - Ramli, Roshahliza M.

AU - Noor, Ali O.Abid

AU - Abdul Samad, Salina

PY - 2017/6/3

Y1 - 2017/6/3

N2 - Some of the teething problems associated in the use of two-sensor noise cancellation systems are the nature of the noise signals—a problem that imposes the use of highly complex algorithms in reducing the noise. The usage of such methods can be impractical for many real time applications, where speed of convergence and processing time are critical. At the same time, the existing approaches are based on using a single, often complex adaptive filter to minimize noise, which has been determined to be inadequate and ineffective. In this paper, a new mechanism is proposed to reduce background noise from speech communications. The procedure is based on a two-sensor adaptive noise canceller that is capable of assigning an appropriate filter adapting to properties of the noise. The criterion to achieve this is based on measuring the eigenvalue spread based on the autocorrelation of the input noise. The proposed noise canceller (INC) applies an adaptive algorithm according to the characteristics of the input signal. Various experiments based on this technique using real-world signals are conducted to gauge the effectiveness of the approach. Initial results illustrated the system capabilities in executing noise cancellation under different types of environmental noise. The results based on the INC technique indicate fast convergence rates; improvements up to 30 dB in signal-to-noise ratio and at the same time shows 65% reduction of computational power compared to conventional method.

AB - Some of the teething problems associated in the use of two-sensor noise cancellation systems are the nature of the noise signals—a problem that imposes the use of highly complex algorithms in reducing the noise. The usage of such methods can be impractical for many real time applications, where speed of convergence and processing time are critical. At the same time, the existing approaches are based on using a single, often complex adaptive filter to minimize noise, which has been determined to be inadequate and ineffective. In this paper, a new mechanism is proposed to reduce background noise from speech communications. The procedure is based on a two-sensor adaptive noise canceller that is capable of assigning an appropriate filter adapting to properties of the noise. The criterion to achieve this is based on measuring the eigenvalue spread based on the autocorrelation of the input noise. The proposed noise canceller (INC) applies an adaptive algorithm according to the characteristics of the input signal. Various experiments based on this technique using real-world signals are conducted to gauge the effectiveness of the approach. Initial results illustrated the system capabilities in executing noise cancellation under different types of environmental noise. The results based on the INC technique indicate fast convergence rates; improvements up to 30 dB in signal-to-noise ratio and at the same time shows 65% reduction of computational power compared to conventional method.

KW - Adaptive algorithms

KW - Adaptive filtering

KW - Eigenvalue spread

KW - Environmental noise

KW - Noise cancellation

UR - http://www.scopus.com/inward/record.url?scp=85020087205&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020087205&partnerID=8YFLogxK

U2 - 10.1007/s10772-017-9425-1

DO - 10.1007/s10772-017-9425-1

M3 - Article

SP - 1

EP - 8

JO - International Journal of Speech Technology

JF - International Journal of Speech Technology

SN - 1381-2416

ER -