Speech enhancement using degenerate unmixing estimation technique and adaptive noise cancellation technique as a post signal processing

Abrar Hussain, Kalaivani Chell, M. Siti Zamratol

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

2 Citations (Scopus)

Abstract

Speech enhancement in degenerate mixtures is a challenging task for the signal processing engineers. Degenerate Unmixing Estimation Technique (DUET) is a commonly used algorithm in speech signal separation, however there are limitations in separating the speech babble as noise and/or competing speech as noise from speech signal. These noises are important for auditory related training and testing. In this research an enhanced approach has been adopted by pairing DUET with Adaptive Noise Cancellation (ANC) which acts as the post-processor. Results from the correlation analysis and spectrogram analysis show that DUET provides separation quality correlation value of minimum 0.57 when speech signals are separated from speech babble and maximum of 0.75 when speech signal is separated from competing speech. On the contrary, both of these minimum and maximum correlation values reach to 0.77 and 0.88 when ANC is used as a postprocessor. The pairing of DUET with ANC has provided a good separation in the tested speech signals.

Original languageEnglish
Title of host publicationIECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages280-285
Number of pages6
ISBN (Electronic)9781467377911
DOIs
Publication statusPublished - 3 Feb 2017
Event2016 IEEE-EMBS Conference on Biomedical Engineering and Sciences, IECBES 2016 - Kuala Lumpur, Malaysia
Duration: 4 Dec 20168 Dec 2016

Other

Other2016 IEEE-EMBS Conference on Biomedical Engineering and Sciences, IECBES 2016
CountryMalaysia
CityKuala Lumpur
Period4/12/168/12/16

Fingerprint

Speech enhancement
cancellation
signal processing
Signal processing
augmentation
spectrograms
engineers
central processing units
education
Engineers

Keywords

  • adaptive noise cancellation
  • anechoic mixing
  • degenerate unmixing estimation technique
  • sparsity
  • speech separation

ASJC Scopus subject areas

  • Biomedical Engineering
  • Instrumentation

Cite this

Hussain, A., Chell, K., & Zamratol, M. S. (2017). Speech enhancement using degenerate unmixing estimation technique and adaptive noise cancellation technique as a post signal processing. In IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences (pp. 280-285). [7843458] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IECBES.2016.7843458

Speech enhancement using degenerate unmixing estimation technique and adaptive noise cancellation technique as a post signal processing. / Hussain, Abrar; Chell, Kalaivani; Zamratol, M. Siti.

IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences. Institute of Electrical and Electronics Engineers Inc., 2017. p. 280-285 7843458.

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

Hussain, A, Chell, K & Zamratol, MS 2017, Speech enhancement using degenerate unmixing estimation technique and adaptive noise cancellation technique as a post signal processing. in IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences., 7843458, Institute of Electrical and Electronics Engineers Inc., pp. 280-285, 2016 IEEE-EMBS Conference on Biomedical Engineering and Sciences, IECBES 2016, Kuala Lumpur, Malaysia, 4/12/16. https://doi.org/10.1109/IECBES.2016.7843458
Hussain A, Chell K, Zamratol MS. Speech enhancement using degenerate unmixing estimation technique and adaptive noise cancellation technique as a post signal processing. In IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences. Institute of Electrical and Electronics Engineers Inc. 2017. p. 280-285. 7843458 https://doi.org/10.1109/IECBES.2016.7843458
Hussain, Abrar ; Chell, Kalaivani ; Zamratol, M. Siti. / Speech enhancement using degenerate unmixing estimation technique and adaptive noise cancellation technique as a post signal processing. IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 280-285
@inproceedings{1617f9b7c8bd47da96dc7ec5cd581253,
title = "Speech enhancement using degenerate unmixing estimation technique and adaptive noise cancellation technique as a post signal processing",
abstract = "Speech enhancement in degenerate mixtures is a challenging task for the signal processing engineers. Degenerate Unmixing Estimation Technique (DUET) is a commonly used algorithm in speech signal separation, however there are limitations in separating the speech babble as noise and/or competing speech as noise from speech signal. These noises are important for auditory related training and testing. In this research an enhanced approach has been adopted by pairing DUET with Adaptive Noise Cancellation (ANC) which acts as the post-processor. Results from the correlation analysis and spectrogram analysis show that DUET provides separation quality correlation value of minimum 0.57 when speech signals are separated from speech babble and maximum of 0.75 when speech signal is separated from competing speech. On the contrary, both of these minimum and maximum correlation values reach to 0.77 and 0.88 when ANC is used as a postprocessor. The pairing of DUET with ANC has provided a good separation in the tested speech signals.",
keywords = "adaptive noise cancellation, anechoic mixing, degenerate unmixing estimation technique, sparsity, speech separation",
author = "Abrar Hussain and Kalaivani Chell and Zamratol, {M. Siti}",
year = "2017",
month = "2",
day = "3",
doi = "10.1109/IECBES.2016.7843458",
language = "English",
pages = "280--285",
booktitle = "IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Speech enhancement using degenerate unmixing estimation technique and adaptive noise cancellation technique as a post signal processing

AU - Hussain, Abrar

AU - Chell, Kalaivani

AU - Zamratol, M. Siti

PY - 2017/2/3

Y1 - 2017/2/3

N2 - Speech enhancement in degenerate mixtures is a challenging task for the signal processing engineers. Degenerate Unmixing Estimation Technique (DUET) is a commonly used algorithm in speech signal separation, however there are limitations in separating the speech babble as noise and/or competing speech as noise from speech signal. These noises are important for auditory related training and testing. In this research an enhanced approach has been adopted by pairing DUET with Adaptive Noise Cancellation (ANC) which acts as the post-processor. Results from the correlation analysis and spectrogram analysis show that DUET provides separation quality correlation value of minimum 0.57 when speech signals are separated from speech babble and maximum of 0.75 when speech signal is separated from competing speech. On the contrary, both of these minimum and maximum correlation values reach to 0.77 and 0.88 when ANC is used as a postprocessor. The pairing of DUET with ANC has provided a good separation in the tested speech signals.

AB - Speech enhancement in degenerate mixtures is a challenging task for the signal processing engineers. Degenerate Unmixing Estimation Technique (DUET) is a commonly used algorithm in speech signal separation, however there are limitations in separating the speech babble as noise and/or competing speech as noise from speech signal. These noises are important for auditory related training and testing. In this research an enhanced approach has been adopted by pairing DUET with Adaptive Noise Cancellation (ANC) which acts as the post-processor. Results from the correlation analysis and spectrogram analysis show that DUET provides separation quality correlation value of minimum 0.57 when speech signals are separated from speech babble and maximum of 0.75 when speech signal is separated from competing speech. On the contrary, both of these minimum and maximum correlation values reach to 0.77 and 0.88 when ANC is used as a postprocessor. The pairing of DUET with ANC has provided a good separation in the tested speech signals.

KW - adaptive noise cancellation

KW - anechoic mixing

KW - degenerate unmixing estimation technique

KW - sparsity

KW - speech separation

UR - http://www.scopus.com/inward/record.url?scp=85015630782&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015630782&partnerID=8YFLogxK

U2 - 10.1109/IECBES.2016.7843458

DO - 10.1109/IECBES.2016.7843458

M3 - Conference contribution

AN - SCOPUS:85015630782

SP - 280

EP - 285

BT - IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences

PB - Institute of Electrical and Electronics Engineers Inc.

ER -