Oracle estimators for the benchmarking of source separation algorithms

Authors:
Emmanuel Vincent;Rémi Gribonval;Mark D. Plumbley
Affiliations:
METISS group, IRISA-INRIA, Campus de Beaulieu, 35042 Rennes CEDEX, France;METISS group, IRISA-INRIA, Campus de Beaulieu, 35042 Rennes CEDEX, France;Center for Digital Music, Department of Electronic Engineering, Queen Mary, University of London, Mile End Road, London E1 4NS, United Kingdom
Venue:
Signal Processing
Year:
2007

Citing 4
Cited 13

Blind separation of speech mixtures via time-frequency masking

IEEE Transactions on Signal Processing
Blind separation of instantaneous mixtures of nonstationary sources

IEEE Transactions on Signal Processing
Experimental upper bound for the performance of convolutive source separation methods

IEEE Transactions on Signal Processing
Performance measurement in blind audio source separation

IEEE Transactions on Audio, Speech, and Language Processing

On the optimality of ideal binary time-frequency masks

Speech Communication
Extension of Sparse, Adaptive Signal Decompositions to Semi-blind Audio Source Separation

ICA '09 Proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation
Validity of the Independence Assumption for the Separation of Instantaneous and Convolutive Mixtures of Speech and Music Sources

ICA '09 Proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation
A Uniform Framework for Ad-Hoc Indexes to Answer Reachability Queries on Large Graphs

DASFAA '09 Proceedings of the 14th International Conference on Database Systems for Advanced Applications
Underdetermined Instantaneous Audio Source Separation via Local Gaussian Modeling

ICA '09 Proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation
Complex nonconvex lp norm minimization for underdetermined source separation

ICA'07 Proceedings of the 7th international conference on Independent component analysis and signal separation
A robust method to count and locate audio sources in a multichannel underdetermined mixture

IEEE Transactions on Signal Processing
Monaural speech/music source separation using discrete energy separation algorithm

Signal Processing
Beyond the narrowband approximation: wideband convex methods for under-determined reverberant audio source separation

IEEE Transactions on Audio, Speech, and Language Processing - Special issue on processing reverberant speech: methodologies and applications
The 2010 signal separation evaluation campaign (SiSEC2010): audio source separation

LVA/ICA'10 Proceedings of the 9th international conference on Latent variable analysis and signal separation
Interactive music with active audio CDs

CMMR'10 Proceedings of the 7th international conference on Exploring music contents
The signal separation evaluation campaign (2007-2010): Achievements and remaining challenges

Signal Processing
The 2011 signal separation evaluation campaign (SiSEC2011): - audio source separation -

LVA/ICA'12 Proceedings of the 10th international conference on Latent Variable Analysis and Signal Separation

Quantified Score

Hi-index	0.08

Visualization

Abstract

Source separation is a difficult problem for which many algorithms have been proposed. In this article, we define oracle estimators which compute the best performance achievable by different classes of algorithms on a given mixture, in a theoretical evaluation framework where the reference sources are available. We describe explicit oracle estimators for three particular classes of algorithms: multichannel time-invariant filtering, single-channel time-frequency masking and multichannel time-frequency masking. We evaluate their performance on various audio mixtures and study their robustness. We draw several conclusions for their three typical applications, namely providing performance bounds for existing and future blind algorithms, selecting the best class of algorithms for a given mixture and assessing the separation difficulty. In particular, we show that it is worth developing blind time-frequency masking algorithms relaxing the common assumption of a single active source per time-frequency point.