An Approximate Bayesian Fundamental Frequency Estimator

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

3 Citationer (Scopus)
333 Downloads (Pure)

Resumé

Joint fundamental frequency and model order estimation is an important problem in several applications such as speech and music processing. In this paper, we develop an approximate estimation algorithm of these quantities using Bayesian inference. The inference about the fundamental frequency and the model order is based on a probability model which corresponds to a minimum of prior information. From this probability model, we give the exact posterior distributions on the fundamental frequency and the model order, and we also present analytical approximations of these distributions which lower the computational load of the algorithm. By use of simulations on both a synthetic signal and a speech signal, the algorithm is demonstrated to be more accurate than a state-of-the-art maximum likelihood-based method.
OriginalsprogEngelsk
Titel2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Antal sider4
ForlagIEEE Press
Publikationsdatomar. 2012
Sider4617-4620
ISBN (Trykt)978-1-4673-0045-2
ISBN (Elektronisk)978-1-4673-0044-5
DOI
StatusUdgivet - mar. 2012
BegivenhedIEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP - Kyoto, Japan
Varighed: 25 mar. 201230 mar. 2012

Konference

KonferenceIEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP
LandJapan
ByKyoto
Periode25/03/201230/03/2012
NavnI E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
ISSN1520-6149

Fingerprint

Maximum likelihood
Processing

Citer dette

Nielsen, J. K., Christensen, M. G., & Jensen, S. H. (2012). An Approximate Bayesian Fundamental Frequency Estimator. I 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (s. 4617-4620). IEEE Press. I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings https://doi.org/10.1109/ICASSP.2012.6288947
Nielsen, Jesper Kjær ; Christensen, Mads Græsbøll ; Jensen, Søren Holdt. / An Approximate Bayesian Fundamental Frequency Estimator. 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE Press, 2012. s. 4617-4620 (I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings).
@inproceedings{283f5405ee124ddeb533f0c13964b13e,
title = "An Approximate Bayesian Fundamental Frequency Estimator",
abstract = "Joint fundamental frequency and model order estimation is an important problem in several applications such as speech and music processing. In this paper, we develop an approximate estimation algorithm of these quantities using Bayesian inference. The inference about the fundamental frequency and the model order is based on a probability model which corresponds to a minimum of prior information. From this probability model, we give the exact posterior distributions on the fundamental frequency and the model order, and we also present analytical approximations of these distributions which lower the computational load of the algorithm. By use of simulations on both a synthetic signal and a speech signal, the algorithm is demonstrated to be more accurate than a state-of-the-art maximum likelihood-based method.",
author = "Nielsen, {Jesper Kj{\ae}r} and Christensen, {Mads Gr{\ae}sb{\o}ll} and Jensen, {S{\o}ren Holdt}",
year = "2012",
month = "3",
doi = "10.1109/ICASSP.2012.6288947",
language = "English",
isbn = "978-1-4673-0045-2",
series = "I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings",
publisher = "IEEE Press",
pages = "4617--4620",
booktitle = "2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

}

Nielsen, JK, Christensen, MG & Jensen, SH 2012, An Approximate Bayesian Fundamental Frequency Estimator. i 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE Press, I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings, s. 4617-4620, IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP, Kyoto, Japan, 25/03/2012. https://doi.org/10.1109/ICASSP.2012.6288947

An Approximate Bayesian Fundamental Frequency Estimator. / Nielsen, Jesper Kjær; Christensen, Mads Græsbøll; Jensen, Søren Holdt.

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE Press, 2012. s. 4617-4620 (I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings).

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - An Approximate Bayesian Fundamental Frequency Estimator

AU - Nielsen, Jesper Kjær

AU - Christensen, Mads Græsbøll

AU - Jensen, Søren Holdt

PY - 2012/3

Y1 - 2012/3

N2 - Joint fundamental frequency and model order estimation is an important problem in several applications such as speech and music processing. In this paper, we develop an approximate estimation algorithm of these quantities using Bayesian inference. The inference about the fundamental frequency and the model order is based on a probability model which corresponds to a minimum of prior information. From this probability model, we give the exact posterior distributions on the fundamental frequency and the model order, and we also present analytical approximations of these distributions which lower the computational load of the algorithm. By use of simulations on both a synthetic signal and a speech signal, the algorithm is demonstrated to be more accurate than a state-of-the-art maximum likelihood-based method.

AB - Joint fundamental frequency and model order estimation is an important problem in several applications such as speech and music processing. In this paper, we develop an approximate estimation algorithm of these quantities using Bayesian inference. The inference about the fundamental frequency and the model order is based on a probability model which corresponds to a minimum of prior information. From this probability model, we give the exact posterior distributions on the fundamental frequency and the model order, and we also present analytical approximations of these distributions which lower the computational load of the algorithm. By use of simulations on both a synthetic signal and a speech signal, the algorithm is demonstrated to be more accurate than a state-of-the-art maximum likelihood-based method.

UR - http://www.scopus.com/inward/record.url?scp=84867619223&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2012.6288947

DO - 10.1109/ICASSP.2012.6288947

M3 - Article in proceeding

SN - 978-1-4673-0045-2

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

SP - 4617

EP - 4620

BT - 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - IEEE Press

ER -

Nielsen JK, Christensen MG, Jensen SH. An Approximate Bayesian Fundamental Frequency Estimator. I 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE Press. 2012. s. 4617-4620. (I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings). https://doi.org/10.1109/ICASSP.2012.6288947