Bayesian periodogram smoothing for speech enhancement

Xueru Zhang; Alexander Ypma; Bert de Vries

Bayesian periodogram smoothing for speech enhancement

Xueru Zhang
, Alexander Ypma
, Bert de Vries

Signal Processing Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Periodogram smoothing of the received noisy signal is a challenging problem in speech enhancement. We present a Bayesian approach, where the instantaneous periodogram is smoothed through an adaptive smoothing parameter. By updating sufficient statistics using new samples of the noisy signal, the smoothing parameter is adjusted on-line. The performance of the novel smoothing algorithm is studied in a speech enhancement context. It is demonstrated that with respect to Mean Square Error, the proposed Bayesian smoothing algorithm performs better than the other non-Bayesian smoothing algorithms in higher signal-to-noise ratio environments.

Original language	English
Title of host publication	Advances in computational intelligence and learning: 17th European Symposium on Artificial Neural Networks ; ESANN 2009 ; Bruges, Belgium, April 22 - 23 - 24, 2009 ; proceedings
Editors	Michel Verleysen
Pages	135-140
Number of pages	6
Publication status	Published - 1 Dec 2009
Event	17th European Symposium on Artificial Neural Networks Computational Intelligence and Machine Learning (ESANN 2009) - Bruges, Belgium Duration: 22 Apr 2009 → 24 Apr 2009 Conference number: 17

Conference

Conference	17th European Symposium on Artificial Neural Networks Computational Intelligence and Machine Learning (ESANN 2009)
Abbreviated title	ESANN 2009
Country/Territory	Belgium
City	Bruges
Period	22/04/09 → 24/04/09
Other	"Advances in Computational Intelligence and Learning"

Access to Document

http://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2009-62.pdf

Cite this

Zhang, X., Ypma, A., & de Vries, B. (2009). Bayesian periodogram smoothing for speech enhancement. In M. Verleysen (Ed.), Advances in computational intelligence and learning: 17th European Symposium on Artificial Neural Networks ; ESANN 2009 ; Bruges, Belgium, April 22 - 23 - 24, 2009 ; proceedings (pp. 135-140) http://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2009-62.pdf

@inproceedings{ddc34a2d92444c5e90f9a38ce2c90764,

title = "Bayesian periodogram smoothing for speech enhancement",

abstract = "Periodogram smoothing of the received noisy signal is a challenging problem in speech enhancement. We present a Bayesian approach, where the instantaneous periodogram is smoothed through an adaptive smoothing parameter. By updating sufficient statistics using new samples of the noisy signal, the smoothing parameter is adjusted on-line. The performance of the novel smoothing algorithm is studied in a speech enhancement context. It is demonstrated that with respect to Mean Square Error, the proposed Bayesian smoothing algorithm performs better than the other non-Bayesian smoothing algorithms in higher signal-to-noise ratio environments.",

author = "Xueru Zhang and Alexander Ypma and \{de Vries\}, Bert",

year = "2009",

month = dec,

day = "1",

language = "English",

isbn = "2-930307-09-9 ",

pages = "135--140",

editor = "Michel Verleysen",

booktitle = "Advances in computational intelligence and learning: 17th European Symposium on Artificial Neural Networks ; ESANN 2009 ; Bruges, Belgium, April 22 - 23 - 24, 2009 ; proceedings",

note = "17th European Symposium on Artificial Neural Networks Computational Intelligence and Machine Learning (ESANN 2009), ESANN 2009 ; Conference date: 22-04-2009 Through 24-04-2009",

}

Zhang, X, Ypma, A & de Vries, B 2009, Bayesian periodogram smoothing for speech enhancement. in M Verleysen (ed.), Advances in computational intelligence and learning: 17th European Symposium on Artificial Neural Networks ; ESANN 2009 ; Bruges, Belgium, April 22 - 23 - 24, 2009 ; proceedings. pp. 135-140, 17th European Symposium on Artificial Neural Networks Computational Intelligence and Machine Learning (ESANN 2009), Bruges, Belgium, 22/04/09. <http://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2009-62.pdf>

Bayesian periodogram smoothing for speech enhancement. / Zhang, Xueru; Ypma, Alexander; de Vries, Bert.
Advances in computational intelligence and learning: 17th European Symposium on Artificial Neural Networks ; ESANN 2009 ; Bruges, Belgium, April 22 - 23 - 24, 2009 ; proceedings. ed. / Michel Verleysen. 2009. p. 135-140.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Bayesian periodogram smoothing for speech enhancement

AU - Zhang, Xueru

AU - Ypma, Alexander

AU - de Vries, Bert

N1 - Conference code: 17

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Periodogram smoothing of the received noisy signal is a challenging problem in speech enhancement. We present a Bayesian approach, where the instantaneous periodogram is smoothed through an adaptive smoothing parameter. By updating sufficient statistics using new samples of the noisy signal, the smoothing parameter is adjusted on-line. The performance of the novel smoothing algorithm is studied in a speech enhancement context. It is demonstrated that with respect to Mean Square Error, the proposed Bayesian smoothing algorithm performs better than the other non-Bayesian smoothing algorithms in higher signal-to-noise ratio environments.

AB - Periodogram smoothing of the received noisy signal is a challenging problem in speech enhancement. We present a Bayesian approach, where the instantaneous periodogram is smoothed through an adaptive smoothing parameter. By updating sufficient statistics using new samples of the noisy signal, the smoothing parameter is adjusted on-line. The performance of the novel smoothing algorithm is studied in a speech enhancement context. It is demonstrated that with respect to Mean Square Error, the proposed Bayesian smoothing algorithm performs better than the other non-Bayesian smoothing algorithms in higher signal-to-noise ratio environments.

UR - https://www.scopus.com/pages/publications/84886995932

M3 - Conference contribution

AN - SCOPUS:84886995932

SN - 2-930307-09-9

SN - 978-2-930307-09-1

SP - 135

EP - 140

BT - Advances in computational intelligence and learning: 17th European Symposium on Artificial Neural Networks ; ESANN 2009 ; Bruges, Belgium, April 22 - 23 - 24, 2009 ; proceedings

A2 - Verleysen, Michel

T2 - 17th European Symposium on Artificial Neural Networks Computational Intelligence and Machine Learning (ESANN 2009)

Y2 - 22 April 2009 through 24 April 2009

ER -

Bayesian periodogram smoothing for speech enhancement

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this