• Publications
  • Influence
Multipitch Estimation of Piano Sounds Using a New Probabilistic Spectral Smoothness Principle
TLDR
A new method for the estimation of multiple concurrent pitches in piano recordings is presented. Expand
  • 287
  • 30
  • PDF
Fast approximated power iteration subspace tracking
TLDR
This paper introduces a fast implementation of the power iteration method for subspace tracking, based on an approximation that is less restrictive than the well-known projection approximation. Expand
  • 159
  • 22
  • PDF
Source/Filter Model for Unsupervised Main Melody Extraction From Polyphonic Audio Signals
TLDR
In this paper, we propose a new approach for the estimation and extraction of the main melody (and in particular the leading vocal part) from polyphonic audio signals. Expand
  • 173
  • 21
  • PDF
Vocal detection in music with support vector machines
TLDR
We propose a statistical learning approach for the automatic detection of vocal regions in a polyphonic musical signal. Expand
  • 80
  • 17
  • PDF
A Musically Motivated Mid-Level Representation for Pitch Estimation and Musical Audio Source Separation
TLDR
We propose a source/filter signal model which provides a mid-level representation of an audio mixture power spectrum as a decomposition onto a dictionary of pre-defined spectral shapes. Expand
  • 144
  • 13
  • PDF
A new perturbation analysis for signal enumeration in rotational invariance techniques
TLDR
We analyze the perturbation induced by an erroneous model order, and we present an error bound for the estimated parameters. Expand
  • 83
  • 11
  • PDF
Selecting the modeling order for the ESPRIT high resolution method: an alternative approach
TLDR
We show that applying the ESPRIT algorithm with an under-estimated model order generates biased frequency estimates. Expand
  • 50
  • 10
  • PDF
Musical instrument recognition by pairwise classification strategies
TLDR
We have shown that it is very advantageous to perform feature selection class pairwise, looking for the subsets of features that enable the best discrimination between any possible pair of instrument classes. Expand
  • 114
  • 9
  • PDF
Score informed audio source separation using a parametric model of non-negative spectrogram
TLDR
In this paper we present a new technique for monaural source separation in musical mixtures, which uses the knowledge of the musical score. Expand
  • 97
  • 9
  • PDF
Time-dependent parametric and harmonic templates in non-negative matrix factorization
This paper presents a new method to decompose musical spectrograms derived from Non-negative Matrix Factorization (NMF). This method uses time-varying harmonic templates (atoms) which are parametric:Expand
  • 40
  • 8
  • PDF
...
1
2
3
4
5
...