Software for audio applications
FASST – Flexible Audio Source Separation Toolbox (2012)
Contributed by Alexey Ozerov, Emmanuel Vincent and Frédéric Bimbot
Programming language: Matlab
Download the software
Reference paper: A. Ozerov, E. Vincent and F. Bimbot, “A general flexible framework for the handling of prior information in audio source separation,” IEEE Trans. on Audio, Speech and Lang. Proc., vol. 20, no. 4, pp. 1118-1133, 2012.
BSS Locate – A toolbox for source localization in stereo convolutive audio mixtures (2012)
Contributed by Charles Blandin, Alexey Ozerov and Emmanuel Vincent
Programming language: Matlab
Download the software
Reference paper: C. Blandin, A. Ozerov and E. Vincent, “Multi-source TDOA estimation in reverberant audio using angular spectra and clustering,” Signal Processing, special issue on “Latent Variable Analysis and Signal Separation”, vol. 92, no. 8, pp. 1950-1960, 2012.
Probabilistic model for main melody extraction using constant-Q transform (2012)
Contributed by Benoit Fuentes, Antoine Liutkus, Roland Badeau and Gaël Richard
Programming language: Matlab
Download the software
This algorithm performs blind main melody extraction. It is the Matlab code corresponding to the system described in Fuentes, Liutkus, Badeau and Richard, ICASSP, 2012
Multichannel harmonic and percussive component separation for music signals (2011)
Contributed by Ngoc Q. K. Duong and Emmanuel Vincent
Programming language: Matlab
Download the software
Reference paper: “Multichannel harmonic and percussive component separation by joint modeling of spatial and spectral continuity”, Proc. 36th IEEE ICASSP, pp. 205-208, 2011.
Multichannel nonnegative matrix factorization toolbox (2010)
Contributed by Alexey Ozerov and Cédric Févotte
Programming language: Matlab
Download the software
Reference paper: A. Ozerov and C. Févotte, “Multichannel nonnegative matrix factorization in convolutive mixtures for audio source separation,” IEEE Trans. on Audio, Speech and Lang. Proc. special issue on Signal Models and Representations of Musical and Environmental Sounds, vol. 18, no. 3, pp. 550-563, March 2010.
Audio source separation using full-rank spatial covariance model (2010)
Contributed by Ngoc Q. K. Duong and Emmanuel Vincent
Programming language: Matlab
Download the software
Reference paper: “Under-determined reverberant audio source separation using a full-rank spatial covariance model”, IEEE Transactions on Audio, Speech and Language Processing, Vol. 18, No. 7, pp. 1830-1840, 2010.
BSS Eval toolbox for performance measurement (2008)
Contributed by Emmanuel Vincent (version 3.0) and by Cédric Févotte, Rémi Gribonval and Emmanuel Vincent (earlier versions)
Programming language: Matlab
Download the software
BSS Eval is a MATLAB toolbox to measure the performance of source separation algorithms given reference signals. The measures are based on the decomposition of each estimated source signal into a number of contributions corresponding to the target source, interference from unwanted sources, and artifacts such as “musical noise”. They are valid for any mixture (instantaneous, convolutive, etc), any source separation task (estimation of single-channel sources vs. multi-channel source images) and any algorithm (beamforming, ICA, time-frequency masking, etc).
Fixed-point frequency domain ICA algorithm for the separation of convolutive mixture of speech (2005)
Contributed by Rajkishore Prasad
Programming language: Matlab
Download the software
This is fixed-point frequency domain ICA algorithm for the separation of convolutive mixture of speech. The proposed algorithms is based on statistical modeling of time-series of speech spectral components by exponential power distribution and its application in the fixed-point algorithm proposed by Aapo Hyvarinen. This GUI can be used to capture speech signal with two element linear microphone array for separation< by fixed-point frequency domain ICA.
ICA for convolutive speech mixture (1998)
Contributed by Shiro Ikeda
Programming language: C and Matlab
Download the software
This is the code for the time-frequency domain ICA algorithm described in Murata, Ikeda and Ziehe, Neurocomputing, 2001.