Abstract
In modelling nonstationary sources, one possible strategy is to define a latent process of strictly positive variables to model variations in second order statistics of the underlying process. This can be achieved, for example, by passing a Gaussian process through a positive nonlinearity or defining a discrete state Markov chain where each state encodes a certain regime. However, models with such constructs turn out to be either not very flexible or non-conjugate, making inference somewhat harder. In this paper, we introduce a conjugate (inverse-) gamma Markov Random field model that allows random fluctuations on variances which are useful as priors for nonstationary time-frequency energy distributions. The main idea is to introduce auxiliary variables such that full conditional distributions and sufficient statistics are readily available as closed form expressions. This allows straightforward implementation of a Gibbs sampler or a variational algorithm. We illustrate our approach on denoising and single channel source separation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Attias, H.: Independent factor analysis. Neural Computation 11(4), 803–851 (1999)
Cemgil, A.T., Fevotte, C., Godsill, S.J.: Variational and Stochastic Inference for Bayesian Source Separation. Digital Signal Processing (in print, 2007)
Cichocki, A., Amari, S.I: Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications, revised version edition. Wiley, Chichester (2003)
Févotte, C., Daudet, L., Godsill, S.J., Torrésani, B.: Sparse regression with structured priors: Application to audio denoising. In: Proc. ICASSP, Toulouse, France (May 2006)
Hyvärinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. John Wiley & Sons, New York (2001)
Knuth, K.H.: Bayesian source separation and localization. In: SPIE 1998: Bayesian Inference for Inverse Problems, San diego, pp. 147–158 (July 1998)
Liu, J.S.: Monte Carlo strategies in scientific computing. Springer, Heidelberg (2004)
MacKay, D.J.C.: Information Theory, Inference and Learning Algorithms. Cambridge University Press, Cambridge (2003)
Miskin, J., Mackay, D.: Ensemble learning for blind source separation. In: Roberts, S.J., Everson, R.M. (eds.) Independent Component Analysis, pp. 209–233. Cambridge University Press, Cambridge (2001)
Reyes-Gomez, M., Jojic, N., Ellis, D.: Deformable spectrograms. In: AI and Statistics Conference, Barbados (2005)
Rowe, D.B.: A Bayesian approach to blind source separation. Journal of Interdisciplinary Mathematics 5(1), 49–76 (2002)
Shepard, N. (ed.): Stochastic Volatility, Selected Readings. Oxford University Press, Oxford (2005)
Wainwright, M., Jordan, M.I.: Graphical models, exponential families, and variational inference. Technical Report 649, Department of Statistics, UC Berkeley (September 2003)
Wolfe, P.J., Godsill, S.J., Ng, W.J.: Bayesian variable selection and regularisation for time-frequency surface estimation. Journal of the Royal Statistical Society (2004)
Wolpert, R.L., Ickstadt, K.: Poisson/gamma random field models for spatial statistics. Biometrica (1998)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cemgil, A.T., Dikmen, O. (2007). Conjugate Gamma Markov Random Fields for Modelling Nonstationary Sources. In: Davies, M.E., James, C.J., Abdallah, S.A., Plumbley, M.D. (eds) Independent Component Analysis and Signal Separation. ICA 2007. Lecture Notes in Computer Science, vol 4666. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74494-8_87
Download citation
DOI: https://doi.org/10.1007/978-3-540-74494-8_87
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74493-1
Online ISBN: 978-3-540-74494-8
eBook Packages: Computer ScienceComputer Science (R0)