Bayesian interpolation in a dynamic sinusoidal model with application to packet-loss concealment

Jesper Kjær Nielsen; Mads Græsbøll Christensen; Ali Taylan Cemgil; Simon J. Godsill; Søren Holdt Jensen

Bayesian interpolation in a dynamic sinusoidal model with application to packet-loss concealment

Jesper Kjær Nielsen, Mads Græsbøll Christensen, Ali Taylan Cemgil, Simon J. Godsill, Søren Holdt Jensen

Research output: Contribution to journal › Conference article in Journal › Research › peer-review

3 Citations (Scopus)

195 Downloads (Pure)

Abstract

In this paper, we consider Bayesian interpolation and parameter estimation in a dynamic sinusoidal model. This model is more ﬂexible than the static sinusoidal model since it enables the amplitudes and phases of the sinusoids to be time-varying. For the dynamic sinusoidal model, we derive a Bayesian inference scheme for the missing observations, hidden states and model parameters of the dynamic model. The inference scheme is based on a Markov chain Monte Carlo method known as Gibbs sampler. We illustrate the performance of the inference scheme to the application of packet-loss concealment of lost audio and speech packet

Original language	English
Journal	Proceedings of the European Signal Processing Conference
Volume	2010
Pages (from-to)	239-243
ISSN	2076-1465
Publication status	Published - 24 Aug 2010
Event	EUSIPCO 2010 - Aalborg, Denmark Duration: 23 Aug 2010 → …

Conference

Conference	EUSIPCO 2010
Country/Territory	Denmark
City	Aalborg
Period	23/08/2010 → …

Access to Document

Eusipco2010bAccepted author manuscript, 665 KB

http://www.eurasip.org/Proceedings/Eusipco/Eusipco2010/Contents/papers/1569292403.pdf

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{c09321a64c7c4a649bc23681e889419e,

title = "Bayesian interpolation in a dynamic sinusoidal model with application to packet-loss concealment",

abstract = "In this paper, we consider Bayesian interpolation and parameter estimation in a dynamic sinusoidal model. This model is more ﬂexible than the static sinusoidal model since it enables the amplitudes and phases of the sinusoids to be time-varying. For the dynamic sinusoidal model, we derive a Bayesian inference scheme for the missing observations, hidden states and model parameters of the dynamic model. The inference scheme is based on a Markov chain Monte Carlo method known as Gibbs sampler. We illustrate the performance of the inference scheme to the application of packet-loss concealment of lost audio and speech packet",

author = "Nielsen, {Jesper Kj{\ae}r} and Christensen, {Mads Gr{\ae}sb{\o}ll} and Cemgil, {Ali Taylan} and Godsill, {Simon J.} and Jensen, {S{\o}ren Holdt}",

year = "2010",

month = aug,

day = "24",

language = "English",

volume = "2010",

pages = "239--243",

journal = "Proceedings of the European Signal Processing Conference",

issn = "2076-1465",

publisher = "European Association for Signal Processing (EURASIP)",

note = "EUSIPCO 2010 ; Conference date: 23-08-2010",

}

Bayesian interpolation in a dynamic sinusoidal model with application to packet-loss concealment. / Nielsen, Jesper Kjær; Christensen, Mads Græsbøll; Cemgil, Ali Taylan et al.
In: Proceedings of the European Signal Processing Conference, Vol. 2010, 24.08.2010, p. 239-243.

Research output: Contribution to journal › Conference article in Journal › Research › peer-review

TY - GEN

T1 - Bayesian interpolation in a dynamic sinusoidal model with application to packet-loss concealment

AU - Nielsen, Jesper Kjær

AU - Christensen, Mads Græsbøll

AU - Cemgil, Ali Taylan

AU - Godsill, Simon J.

AU - Jensen, Søren Holdt

PY - 2010/8/24

Y1 - 2010/8/24

N2 - In this paper, we consider Bayesian interpolation and parameter estimation in a dynamic sinusoidal model. This model is more ﬂexible than the static sinusoidal model since it enables the amplitudes and phases of the sinusoids to be time-varying. For the dynamic sinusoidal model, we derive a Bayesian inference scheme for the missing observations, hidden states and model parameters of the dynamic model. The inference scheme is based on a Markov chain Monte Carlo method known as Gibbs sampler. We illustrate the performance of the inference scheme to the application of packet-loss concealment of lost audio and speech packet

AB - In this paper, we consider Bayesian interpolation and parameter estimation in a dynamic sinusoidal model. This model is more ﬂexible than the static sinusoidal model since it enables the amplitudes and phases of the sinusoids to be time-varying. For the dynamic sinusoidal model, we derive a Bayesian inference scheme for the missing observations, hidden states and model parameters of the dynamic model. The inference scheme is based on a Markov chain Monte Carlo method known as Gibbs sampler. We illustrate the performance of the inference scheme to the application of packet-loss concealment of lost audio and speech packet

M3 - Conference article in Journal

SN - 2076-1465

VL - 2010

SP - 239

EP - 243

JO - Proceedings of the European Signal Processing Conference

JF - Proceedings of the European Signal Processing Conference

T2 - EUSIPCO 2010

Y2 - 23 August 2010

ER -

Bayesian interpolation in a dynamic sinusoidal model with application to packet-loss concealment

Abstract

Conference

Access to Document

AUB Link

Fingerprint

Cite this