Fast factorization-based inference for Bayesian harmonic models

Abstract : Harmonic sinusoidal models are a fundamental tool for audio signal analysis. Bayesian harmonic models guarantee a good resynthesis quality and allow joint use of learnt parameter priors and auditory motivated distortion measures. However inference algorithms based on Monte Carlo sampling are rather slow for realistic data. In this paper, we investigate fast inference algorithms based on approximate factorization of the joint posterior into a product of independent distributions on small subsets of parameters. We discuss the conditions under which these approximations hold true and evaluate their performance experimentally. We suggest how they could be used together with Monte Carlo algorithms for a faster sampling-based inference.
Liste complète des métadonnées

Cited literature [10 references]  Display  Hide  Download

https://hal.inria.fr/inria-00544652
Contributor : Emmanuel Vincent <>
Submitted on : Wednesday, December 8, 2010 - 3:58:43 PM
Last modification on : Thursday, March 21, 2019 - 2:20:03 PM
Document(s) archivé(s) le : Thursday, March 10, 2011 - 11:29:27 AM

File

vincent_MLSP06.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00544652, version 1

Citation

Emmanuel Vincent, Mark Plumbley. Fast factorization-based inference for Bayesian harmonic models. 2006 IEEE Int. Workshop on Machine Learning for Signal Processing, Sep 2006, Maynooth, Ireland. pp.117--122. ⟨inria-00544652⟩

Share

Metrics

Record views

57

Files downloads

85