Computer Audition Toolbox
Welcome to the Computer Audition Toolbox (CATbox) page. Here you will find the CATbox download page and the documentation page.
This project is meant to be an open repository of tools in computer audition. If you would like to contribute your code, please contact the toolbox managers. All toolbox materials are available under GNU license. The CATbox is a compilation of MATLAB functions that are of interest to computer audition researchers and related fields. The project is meant to collaborative to sustain the growing demands in this new field.
The CATbox is maintained by Shlomo Dubnov and Mehrdad Yazdani.
AudioBasis: (MPEG7) Audio Basis (AB) and several distance measures (using GMM and Itakura Saito).
Auditory: ERB auditory filter bank
Ceps: Cepstral envelope and pitch analysis
Chroma: Chroma representation of spectral magnitudes
ConstQ: Constant-Q filter Bank
FactorOracle: Factor Oracle for Midi improvisation
ISDist: Itakura-Saito Distance between AR spectra
InstFreq: Instantaneous Frequency using Miller’s hop-one method
InfoRate: Information Rate analysis, including signal recurrence analysis by spectral clustering
LPC: Linear Prediction envelope and residual, including simple Talkbox
LSEE: Griffin and Lim’s least square error estimation from spectral magnitudes (phaseless reconstuction)
MFCC: Mel-Frequency Cepstral Coefficients
MIDI Tools: Various Midi representations needed for alignment and improvisation
NoteSigSim: Note-Signal similarity using harmonic projection
Onset: Various methods for onset detection
SFM: Spectral Flatness Measure, including the non-Gaussian version
STFT: Short time Fourier transform, including phase-vocoder time stretching and pitch shifting
SeqAlign: Different sequence alignment and dynamic time warping methods
Utils: some utilities
Welch: Welch spectral estimate
YASA: Sinusoidal and Noise analysis and resynthesis based on Linear Prediction and MVDR
Thanks to: Benjamin Blankertz, Mike Brookes, Michael Casey, Dan Ellis, Malcom Slaney
Other programs needed to run different parts of this toolbox:
Eerola, T. & Toiviainen, P. (2004). MIDI Toolbox
Dan Ellis’s Mp3read for Matlab (with my small modification)
This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You can obtain a copy of the GNU General Public License from ftp://prep.ai.mit.edu/pub/gnu/COPYING-2.0 or by writing to Free Software Foundation, Inc.,675 Mass Ave, Cambridge, MA 02139, USA.