Advanced

Smooth Time-Frequency Estimation using Covariance Fitting

Brynolfsson, Johan LU ; Swärd, Johan LU ; Jakobsson, Andreas LU and Sandsten, Maria LU (2014) 2014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP 2014) p.779-783
Abstract
In this paper, we introduce a time-frequency spectral estimator for smooth spectra, allowing for irregularly sampled measurements. A non-parametric representation of the time dependent (TD) covariance matrix is formed by assuming that the spectrum is piecewise linear. Using this representation, the time-frequency spectrum is then estimated by solving a convex covariance fitting problem, which also, as a byproduct, provides an enhanced estimation of the TD covariance matrix. Numerical examples using simulated non-stationary processes show the preferable performance of the proposed method as compared to the classical Wigner-Ville distribution and a smoothed spectrogram.
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Time-frequency analysis, convex optimization, smooth
host publication
Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on
pages
5 pages
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
2014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP 2014)
conference location
Florence, Italy
conference dates
2014-05-04 - 2014-05-09
external identifiers
  • wos:000343655300157
  • scopus:84905215259
ISSN
1520-6149
DOI
10.1109/ICASSP.2014.6853702
language
English
LU publication?
yes
id
9d959852-d49a-494b-b6b4-18d046c6916e (old id 4588285)
date added to LUP
2014-08-29 20:54:25
date last changed
2019-03-08 02:33:43
@inproceedings{9d959852-d49a-494b-b6b4-18d046c6916e,
  abstract     = {In this paper, we introduce a time-frequency spectral estimator for smooth spectra, allowing for irregularly sampled measurements. A non-parametric representation of the time dependent (TD) covariance matrix is formed by assuming that the spectrum is piecewise linear. Using this representation, the time-frequency spectrum is then estimated by solving a convex covariance fitting problem, which also, as a byproduct, provides an enhanced estimation of the TD covariance matrix. Numerical examples using simulated non-stationary processes show the preferable performance of the proposed method as compared to the classical Wigner-Ville distribution and a smoothed spectrogram.},
  author       = {Brynolfsson, Johan and Swärd, Johan and Jakobsson, Andreas and Sandsten, Maria},
  issn         = {1520-6149},
  keyword      = {Time-frequency analysis,convex optimization,smooth},
  language     = {eng},
  location     = {Florence, Italy},
  pages        = {779--783},
  publisher    = {IEEE--Institute of Electrical and Electronics Engineers Inc.},
  title        = {Smooth Time-Frequency Estimation using Covariance Fitting},
  url          = {http://dx.doi.org/10.1109/ICASSP.2014.6853702},
  year         = {2014},
}