Speech Dereverberation Based on Convex Optimization Algorithms for Group Sparse Linear Prediction

Daniele Giacobello; Tobias Lindstrøm Jensen

doi:10.1109/ICASSP.2018.8462560

Speech Dereverberation Based on Convex Optimization Algorithms for Group Sparse Linear Prediction

Daniele Giacobello, Tobias Lindstrøm Jensen

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

11 Citationer (Scopus)

445 Downloads (Pure)

Abstract

In this paper, we consider methods for improving far-field speech
recognition using dereverberation based on sparse multi-channel linear
prediction. In particular, we extend successful methods based on nonconvex iteratively reweighted least squares, that look for a sparse
desired speech signal in the short-term Fourier transform domain, by proposing sparsity promoting convex functions. Furthermore, we show how to improve performance by applying regularization into both the reweighted least squares and convex methods. We evaluate
the methods using large scale simulations by mimicking the application scenarios of interest. The experiments show that the proposed
convex formulations and regularization offer improvements over existing methods with added robustness and flexibility in fairly different
acoustic scenarios.

Originalsprog	Engelsk
Titel	IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
Antal sider	5
Forlag	IEEE (Institute of Electrical and Electronics Engineers)
Publikationsdato	2018
Sider	446-450
Artikelnummer	8462560
ISBN (Trykt)	978-1-5386-4659-5
ISBN (Elektronisk)	978-1-5386-4658-8
DOI	https://doi.org/10.1109/ICASSP.2018.8462560
Status	Udgivet - 2018
Begivenhed	2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Calgary, Canada Varighed: 15 apr. 2018 → 20 apr. 2018 https://2018.ieeeicassp.org/

Konference

Konference	2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Land/Område	Canada
By	Calgary
Periode	15/04/2018 → 20/04/2018
Internetadresse	https://2018.ieeeicassp.org/

Navn	I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
ISSN	1520-6149

Adgang til dokumentet

10.1109/ICASSP.2018.8462560

sparseLPdereverberationIndsendt manuskript, 220 KB

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Andre filer og links

http://www.scopus.com/inward/record.url?scp=85054203284&partnerID=8YFLogxK

RTC: Computational Oriented Real-time Convex Optimization in Signal Processing
Jensen, T. (Projektdeltager), Jensen, S. H. (Projektdeltager), Larsen, T. (Projektdeltager), Giacobello, D. (Kontaktperson), Dahl, J. (Kontaktperson) & Diehl, M. (Kontaktperson)
The Danish Council for Independent Research| Technology and Production Sciences, Danmarks Frie Forskningsfond | Sapere Aude
01/06/2014 → 30/06/2017
Projekter: Projekt › Forskning

Citationsformater

Giacobello, Daniele ; Jensen, Tobias Lindstrøm. / Speech Dereverberation Based on Convex Optimization Algorithms for Group Sparse Linear Prediction. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018. IEEE (Institute of Electrical and Electronics Engineers), 2018. s. 446-450 (I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings).

@inproceedings{d787ac0c84114f21bfaed63a76f8cc86,

title = "Speech Dereverberation Based on Convex Optimization Algorithms for Group Sparse Linear Prediction",

abstract = "In this paper, we consider methods for improving far-field speechrecognition using dereverberation based on sparse multi-channel linearprediction. In particular, we extend successful methods based on nonconvex iteratively reweighted least squares, that look for a sparsedesired speech signal in the short-term Fourier transform domain, by proposing sparsity promoting convex functions. Furthermore, we show how to improve performance by applying regularization into both the reweighted least squares and convex methods. We evaluatethe methods using large scale simulations by mimicking the application scenarios of interest. The experiments show that the proposedconvex formulations and regularization offer improvements over existing methods with added robustness and flexibility in fairly differentacoustic scenarios.",

author = "Daniele Giacobello and Jensen, {Tobias Lindstr{\o}m}",

year = "2018",

doi = "10.1109/ICASSP.2018.8462560",

language = "English",

isbn = "978-1-5386-4659-5",

series = "I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings",

publisher = "IEEE (Institute of Electrical and Electronics Engineers)",

pages = "446--450",

booktitle = "IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018",

address = "United States",

note = "2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP ; Conference date: 15-04-2018 Through 20-04-2018",

url = "https://2018.ieeeicassp.org/",

}

Giacobello, D & Jensen, TL 2018, Speech Dereverberation Based on Convex Optimization Algorithms for Group Sparse Linear Prediction. i IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018., 8462560, IEEE (Institute of Electrical and Electronics Engineers), I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings, s. 446-450, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Alberta, Canada, 15/04/2018. https://doi.org/10.1109/ICASSP.2018.8462560

Speech Dereverberation Based on Convex Optimization Algorithms for Group Sparse Linear Prediction. / Giacobello, Daniele; Jensen, Tobias Lindstrøm.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018. IEEE (Institute of Electrical and Electronics Engineers), 2018. s. 446-450 8462560 (I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings).

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Speech Dereverberation Based on Convex Optimization Algorithms for Group Sparse Linear Prediction

AU - Giacobello, Daniele

AU - Jensen, Tobias Lindstrøm

PY - 2018

Y1 - 2018

N2 - In this paper, we consider methods for improving far-field speechrecognition using dereverberation based on sparse multi-channel linearprediction. In particular, we extend successful methods based on nonconvex iteratively reweighted least squares, that look for a sparsedesired speech signal in the short-term Fourier transform domain, by proposing sparsity promoting convex functions. Furthermore, we show how to improve performance by applying regularization into both the reweighted least squares and convex methods. We evaluatethe methods using large scale simulations by mimicking the application scenarios of interest. The experiments show that the proposedconvex formulations and regularization offer improvements over existing methods with added robustness and flexibility in fairly differentacoustic scenarios.

AB - In this paper, we consider methods for improving far-field speechrecognition using dereverberation based on sparse multi-channel linearprediction. In particular, we extend successful methods based on nonconvex iteratively reweighted least squares, that look for a sparsedesired speech signal in the short-term Fourier transform domain, by proposing sparsity promoting convex functions. Furthermore, we show how to improve performance by applying regularization into both the reweighted least squares and convex methods. We evaluatethe methods using large scale simulations by mimicking the application scenarios of interest. The experiments show that the proposedconvex formulations and regularization offer improvements over existing methods with added robustness and flexibility in fairly differentacoustic scenarios.

UR - http://www.scopus.com/inward/record.url?scp=85054203284&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2018.8462560

DO - 10.1109/ICASSP.2018.8462560

M3 - Article in proceeding

SN - 978-1-5386-4659-5

T3 - I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings

SP - 446

EP - 450

BT - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018

PB - IEEE (Institute of Electrical and Electronics Engineers)

T2 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Y2 - 15 April 2018 through 20 April 2018

ER -

Giacobello D, Jensen TL. Speech Dereverberation Based on Convex Optimization Algorithms for Group Sparse Linear Prediction. I IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018. IEEE (Institute of Electrical and Electronics Engineers). 2018. s. 446-450. 8462560. (I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings). doi: 10.1109/ICASSP.2018.8462560

Speech Dereverberation Based on Convex Optimization Algorithms for Group Sparse Linear Prediction

Abstract

Konference

Adgang til dokumentet

AUB Link

Andre filer og links

Projekter

RTC: Computational Oriented Real-time Convex Optimization in Signal Processing

Citationsformater