Enforcing sparsity, shift-invariance and positivity in a bayesian model of polyphonic piano music


Blumensath, T. and Davies, M. E. (2005) Enforcing sparsity, shift-invariance and positivity in a bayesian model of polyphonic piano music At IEEE Workshop on Statistical Signal Processing, France. (doi:10.1109/SSP.2005.1628695).

Download

Full text not available from this repository.

Description/Abstract

In this paper we develop a Bayesian method to extract individual
notes from a polyphonic piano recording. The distribution
of the note activation is non-negative and we therefore introduce
a modified Rayleigh distribution to model this note behaviour.
Sparseness of the note activation is achieved by a mixture
distribution that is a mixture of a delta function and the modified
Rayleigh distribution. The used learning rule requires integration
over the note activations, which is done using a Gibbs Sampling
Monte Carlo method. We analyse the behaviour of the algorithm
using a simplified test signal as well as a real piano recording

Item Type: Conference or Workshop Item (Paper)
Digital Object Identifier (DOI): doi:10.1109/SSP.2005.1628695
Venue - Dates: IEEE Workshop on Statistical Signal Processing, France, 2005-07-01
Subjects:
Organisations: Signal Processing & Control Grp
ePrint ID: 151933
Date :
Date Event
July 2005Published
Date Deposited: 01 Jul 2010 10:54
Last Modified: 18 Apr 2017 04:20
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/151933

Actions (login required)

View Item View Item