Dynamic spectral subtraction on AWGN speech

Sukanya Sagarika Meher, T. Ananthakrishna

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

3 Citations (Scopus)

Abstract

To enable accurate exchange of information or data, the quality and intelligibility of speech play an important factor. However, pragmatically the quality of speech is distorted by the presence of background noise. This in turn leads to poor performance of the system as well as causes listener fatigue. To resolve such ambiguity we apply speech enhancement algorithms which improve the intelligibility as well as quality of speech which has been degraded by background noise. In this paper two such algorithms have been discussed for noise reduction. One is conventional spectral subtraction method and the other is the proposed modified version of spectral subtraction. While the former aims to improve speech quality degraded by additive background noise, the latter aims to improve speech quality from dynamic additive noise as well. Modified noise reduction algorithm is compared to conventional spectral subtraction based on SNR improvement introduced by them.

Original languageEnglish
Title of host publication2nd International Conference on Signal Processing and Integrated Networks, SPIN 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages92-97
Number of pages6
ISBN (Electronic)9781479959914
DOIs
Publication statusPublished - 24-04-2015
Event2nd International Conference on Signal Processing and Integrated Networks, SPIN 2015 - Noida, India
Duration: 19-02-201520-02-2015

Conference

Conference2nd International Conference on Signal Processing and Integrated Networks, SPIN 2015
CountryIndia
CityNoida
Period19-02-1520-02-15

Fingerprint

Speech intelligibility
Additive noise
Noise abatement
Speech enhancement
Fatigue of materials

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Meher, S. S., & Ananthakrishna, T. (2015). Dynamic spectral subtraction on AWGN speech. In 2nd International Conference on Signal Processing and Integrated Networks, SPIN 2015 (pp. 92-97). [7095302] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SPIN.2015.7095302
Meher, Sukanya Sagarika ; Ananthakrishna, T. / Dynamic spectral subtraction on AWGN speech. 2nd International Conference on Signal Processing and Integrated Networks, SPIN 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 92-97
@inproceedings{fe7ca47f0c2f41e89cad7761eb81205c,
title = "Dynamic spectral subtraction on AWGN speech",
abstract = "To enable accurate exchange of information or data, the quality and intelligibility of speech play an important factor. However, pragmatically the quality of speech is distorted by the presence of background noise. This in turn leads to poor performance of the system as well as causes listener fatigue. To resolve such ambiguity we apply speech enhancement algorithms which improve the intelligibility as well as quality of speech which has been degraded by background noise. In this paper two such algorithms have been discussed for noise reduction. One is conventional spectral subtraction method and the other is the proposed modified version of spectral subtraction. While the former aims to improve speech quality degraded by additive background noise, the latter aims to improve speech quality from dynamic additive noise as well. Modified noise reduction algorithm is compared to conventional spectral subtraction based on SNR improvement introduced by them.",
author = "Meher, {Sukanya Sagarika} and T. Ananthakrishna",
year = "2015",
month = "4",
day = "24",
doi = "10.1109/SPIN.2015.7095302",
language = "English",
pages = "92--97",
booktitle = "2nd International Conference on Signal Processing and Integrated Networks, SPIN 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Meher, SS & Ananthakrishna, T 2015, Dynamic spectral subtraction on AWGN speech. in 2nd International Conference on Signal Processing and Integrated Networks, SPIN 2015., 7095302, Institute of Electrical and Electronics Engineers Inc., pp. 92-97, 2nd International Conference on Signal Processing and Integrated Networks, SPIN 2015, Noida, India, 19-02-15. https://doi.org/10.1109/SPIN.2015.7095302

Dynamic spectral subtraction on AWGN speech. / Meher, Sukanya Sagarika; Ananthakrishna, T.

2nd International Conference on Signal Processing and Integrated Networks, SPIN 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 92-97 7095302.

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

TY - GEN

T1 - Dynamic spectral subtraction on AWGN speech

AU - Meher, Sukanya Sagarika

AU - Ananthakrishna, T.

PY - 2015/4/24

Y1 - 2015/4/24

N2 - To enable accurate exchange of information or data, the quality and intelligibility of speech play an important factor. However, pragmatically the quality of speech is distorted by the presence of background noise. This in turn leads to poor performance of the system as well as causes listener fatigue. To resolve such ambiguity we apply speech enhancement algorithms which improve the intelligibility as well as quality of speech which has been degraded by background noise. In this paper two such algorithms have been discussed for noise reduction. One is conventional spectral subtraction method and the other is the proposed modified version of spectral subtraction. While the former aims to improve speech quality degraded by additive background noise, the latter aims to improve speech quality from dynamic additive noise as well. Modified noise reduction algorithm is compared to conventional spectral subtraction based on SNR improvement introduced by them.

AB - To enable accurate exchange of information or data, the quality and intelligibility of speech play an important factor. However, pragmatically the quality of speech is distorted by the presence of background noise. This in turn leads to poor performance of the system as well as causes listener fatigue. To resolve such ambiguity we apply speech enhancement algorithms which improve the intelligibility as well as quality of speech which has been degraded by background noise. In this paper two such algorithms have been discussed for noise reduction. One is conventional spectral subtraction method and the other is the proposed modified version of spectral subtraction. While the former aims to improve speech quality degraded by additive background noise, the latter aims to improve speech quality from dynamic additive noise as well. Modified noise reduction algorithm is compared to conventional spectral subtraction based on SNR improvement introduced by them.

UR - http://www.scopus.com/inward/record.url?scp=84947262580&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84947262580&partnerID=8YFLogxK

U2 - 10.1109/SPIN.2015.7095302

DO - 10.1109/SPIN.2015.7095302

M3 - Conference contribution

AN - SCOPUS:84947262580

SP - 92

EP - 97

BT - 2nd International Conference on Signal Processing and Integrated Networks, SPIN 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Meher SS, Ananthakrishna T. Dynamic spectral subtraction on AWGN speech. In 2nd International Conference on Signal Processing and Integrated Networks, SPIN 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 92-97. 7095302 https://doi.org/10.1109/SPIN.2015.7095302