Fault tolerant transform domain adaptive noise canceling from corrupted speech signals

D. Sova; C. Radhakrishnan; W. K. Jenkins; A. D. Salvia

doi:10.1109/MWSCAS.2012.6292163

Fault tolerant transform domain adaptive noise canceling from corrupted speech signals

D. Sova, C. Radhakrishnan, W. K. Jenkins, A. D. Salvia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

Fault Tolerant Adaptive Filters (FTAFs) rely on inherent learning capabilities of the adaptive process to compensate for transient (soft) or permanent (hard) errors in hardware implementations. This paper investigates fault tolerant transform domain adaptive noise canceling filters to cancel noise from corrupted speech signals. Two transform domain adaptive FIR architectures are compared, one based on the conventional FFT and one on the Modified Discrete Fourier Transform (MDFT), both without zero padding. Results support the fact that the MDFT- based FTAF architecture is able to overcome certain fault conditions that cannot be properly handled with a conventional FFT-based FTAF architecture.

Original language	English (US)
Title of host publication	2012 IEEE 55th International Midwest Symposium on Circuits and Systems, MWSCAS 2012
Pages	888-891
Number of pages	4
DOIs	https://doi.org/10.1109/MWSCAS.2012.6292163
State	Published - 2012
Event	2012 IEEE 55th International Midwest Symposium on Circuits and Systems, MWSCAS 2012 - Boise, ID, United States Duration: Aug 5 2012 → Aug 8 2012

Publication series

Name	Midwest Symposium on Circuits and Systems
ISSN (Print)	1548-3746

Other

Other	2012 IEEE 55th International Midwest Symposium on Circuits and Systems, MWSCAS 2012
Country/Territory	United States
City	Boise, ID
Period	8/5/12 → 8/8/12

All Science Journal Classification (ASJC) codes

Electronic, Optical and Magnetic Materials
Electrical and Electronic Engineering

Access to Document

10.1109/MWSCAS.2012.6292163

Cite this

@inproceedings{752520277c694c0ab9ba8b348bdf97ba,

title = "Fault tolerant transform domain adaptive noise canceling from corrupted speech signals",

abstract = "Fault Tolerant Adaptive Filters (FTAFs) rely on inherent learning capabilities of the adaptive process to compensate for transient (soft) or permanent (hard) errors in hardware implementations. This paper investigates fault tolerant transform domain adaptive noise canceling filters to cancel noise from corrupted speech signals. Two transform domain adaptive FIR architectures are compared, one based on the conventional FFT and one on the Modified Discrete Fourier Transform (MDFT), both without zero padding. Results support the fact that the MDFT- based FTAF architecture is able to overcome certain fault conditions that cannot be properly handled with a conventional FFT-based FTAF architecture.",

author = "D. Sova and C. Radhakrishnan and Jenkins, {W. K.} and Salvia, {A. D.}",

year = "2012",

doi = "10.1109/MWSCAS.2012.6292163",

language = "English (US)",

isbn = "9781467325264",

series = "Midwest Symposium on Circuits and Systems",

pages = "888--891",

booktitle = "2012 IEEE 55th International Midwest Symposium on Circuits and Systems, MWSCAS 2012",

note = "2012 IEEE 55th International Midwest Symposium on Circuits and Systems, MWSCAS 2012 ; Conference date: 05-08-2012 Through 08-08-2012",

}

Sova, D, Radhakrishnan, C, Jenkins, WK & Salvia, AD 2012, Fault tolerant transform domain adaptive noise canceling from corrupted speech signals. in 2012 IEEE 55th International Midwest Symposium on Circuits and Systems, MWSCAS 2012., 6292163, Midwest Symposium on Circuits and Systems, pp. 888-891, 2012 IEEE 55th International Midwest Symposium on Circuits and Systems, MWSCAS 2012, Boise, ID, United States, 8/5/12. https://doi.org/10.1109/MWSCAS.2012.6292163

Fault tolerant transform domain adaptive noise canceling from corrupted speech signals. / Sova, D.; Radhakrishnan, C.; Jenkins, W. K. et al.
2012 IEEE 55th International Midwest Symposium on Circuits and Systems, MWSCAS 2012. 2012. p. 888-891 6292163 (Midwest Symposium on Circuits and Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Fault tolerant transform domain adaptive noise canceling from corrupted speech signals

AU - Sova, D.

AU - Radhakrishnan, C.

AU - Jenkins, W. K.

AU - Salvia, A. D.

PY - 2012

Y1 - 2012

N2 - Fault Tolerant Adaptive Filters (FTAFs) rely on inherent learning capabilities of the adaptive process to compensate for transient (soft) or permanent (hard) errors in hardware implementations. This paper investigates fault tolerant transform domain adaptive noise canceling filters to cancel noise from corrupted speech signals. Two transform domain adaptive FIR architectures are compared, one based on the conventional FFT and one on the Modified Discrete Fourier Transform (MDFT), both without zero padding. Results support the fact that the MDFT- based FTAF architecture is able to overcome certain fault conditions that cannot be properly handled with a conventional FFT-based FTAF architecture.

AB - Fault Tolerant Adaptive Filters (FTAFs) rely on inherent learning capabilities of the adaptive process to compensate for transient (soft) or permanent (hard) errors in hardware implementations. This paper investigates fault tolerant transform domain adaptive noise canceling filters to cancel noise from corrupted speech signals. Two transform domain adaptive FIR architectures are compared, one based on the conventional FFT and one on the Modified Discrete Fourier Transform (MDFT), both without zero padding. Results support the fact that the MDFT- based FTAF architecture is able to overcome certain fault conditions that cannot be properly handled with a conventional FFT-based FTAF architecture.

UR - http://www.scopus.com/inward/record.url?scp=84867318444&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867318444&partnerID=8YFLogxK

U2 - 10.1109/MWSCAS.2012.6292163

DO - 10.1109/MWSCAS.2012.6292163

M3 - Conference contribution

AN - SCOPUS:84867318444

SN - 9781467325264

T3 - Midwest Symposium on Circuits and Systems

SP - 888

EP - 891

BT - 2012 IEEE 55th International Midwest Symposium on Circuits and Systems, MWSCAS 2012

T2 - 2012 IEEE 55th International Midwest Symposium on Circuits and Systems, MWSCAS 2012

Y2 - 5 August 2012 through 8 August 2012

ER -

Fault tolerant transform domain adaptive noise canceling from corrupted speech signals

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this