Centre for Digital Music

Seminar Videos
Conferences & Events
PhD Study
PhD Graduates
  Image of audio equipment

Software and Downloads

Software and other downloads created by the Centre for Digital Music.


SoundBite is the quickest and easiest way to create great-sounding playlists in iTunes. Once installed, SoundBite will get to know your music collection and when it's done, you're ready to create playlists to suit your mood with just a couple of mouse clicks!

For further information and downloads, visit:

Sonic Visualiser

Sonic Visualiser is an application for viewing and analysing the contents of music audio files. The aim of Sonic Visualiser is to be the first program you reach for when want to study a musical recording rather than simply listen to it.

As well as a number of features designed to make exploring audio data as revealing and fun as possible, Sonic Visualiser also has powerful annotation capabilities to help you to describe what you find, and the ability to run automated annotation and analysis plugins in the Vamp analysis plugin format – as well as applying standard audio effects.

For more information and downloads, visit:

BeatFX - Beat-synchronous effects

BeatFx is a suite of real-time audio effects that use beat tracking to allow automatic synchronisation of effect parameters to the beat of the input audio.

For further information and downloads, visit the BeatFx page.

aubio - A library for audio labelling

Aubio - a library for real-time audio labelling (version 0.2.0)

aubio is a collection of C routines for real time detection of audio features.

Different functions for onset and pitch detection are included, along with our tempo tracking algorithm.

Copyright 2003,2006: Paul Brossier
License: GNU General Public License


P. Brossier, J. P. Bello and M. D. Plumbley. Real-time temporal segmentation of note objects in music signals, in Proceedings of the International Computer Music Conference (ICMC 2004), Miami, Florida, USA, November 1-6, 2004.

P. Brossier, J. P. Bello and M. D. Plumbley. Fast labelling of notes in music signals, in Proceedings of the 5th International Conference on Music Information Retrieval (ISMIR 2004), Barcelona, Spain, October 10-14, 2004.

Download as . . .

gzipped tar aubio-0.2.0.tar.gz 471 KB

JSLAB - Java Scheme Library (version 0.2)

Copyright 2000,2004: Dr. Samer Abdallah

A Java class library and a bunch of scheme scripts which provide an interactive, interpreted environment for doing mathematical and signal processing experiments.

These tools have been developed as part of the EPSRC project Automatic Polyphonic Music Transcription using Multiple Cause Models and Independent Component Analysis (GR/R54620/01).

Download as . . .

gzipped tar jslab-0.2.tar.gz 2.9 MB
zip file jslab-0.2.zip 4.4 MB

QMLAB - Some Matlab tools (version 0.2)

Copyright (2004): Dr. Samer Abdallah

Miscellaneous Matlab tools for ICA, sparse coding, multidimensional scaling, etc.

These tools have been developed as part of the EPSRC project Automatic Polyphonic Music Transcription using Multiple Cause Models and Independent Component Analysis (GR/R54620/01).

Download as . . .

gzipped tar qmlab-0.2.tar.gz 129 KB
zip file qmlab-0.2.zip 209 KB

MUSHRAM - A Matlab interface for MUSHRA listening tests (version 1.0)

Author: Dr. Emmanuel Vincent (2005)
Distributed under the terms of the GNU General Public License version 2.

MUSHRA means "MUlti Stimulus test with Hidden Reference and Anchor". This is the recommendation ITU-R BS.1534-1 for the subjective assessment of intermediate quality level of coding systems.

MUSHRAM is a graphical interface written in MATLAB language. This means you need MATLAB to run it, but conversely it can run on any platform supporting MATLAB.

The distribution includes a detailed user guide.

This software was developed as part of the EPSRC project "Object-based coding of musical audio" (GR/S75802/01).

Download as . . .

gzipped tar mushram-1.0.tar.gz 196 KB
zip file mushram-1.0.zip 200 KB

Chord Tools & Transcriptions

Author: C. Harte (2005)
Distributed under the terms of the GPL (GNU General Public License).


C.Harte, M. B. Sandler, S. A. Abdallah and E. Gómez: Symbolic Representation of Musical Chords: A Proposed Syntax for Text Annotations. Proceedings of the 6th International Conference on Music Information Retrieval (ISMIR 2005), pp. 66-71.

Available via email. Please contact christopher.harte@elec.qmul.ac.uk

QM Vamp Plugins - Audio feature extraction plugins

Please download from:

Prolog Matlab interface


  • Samer Abdallah, Centre for Digital Music, Queen Mary, University of London
  • Christophe Rhodes, Centre for Computational Creativity, Goldsmiths College, University of London

Dec 2004 - July 2006

PLML is a foreign interface that enables Matlab to be used as a computational engine from within SWI Prolog. The basic idea is that instead of using the standard is/2 operator to evaluate a certain class of terms, we can use the ===/2 operator to get Matlab to evaluate a (much richer) class of terms, eg

?- float(A)===trace(eye(3)).

A = 3.0

We can also get Matlab to perform actions with side effects, like making sounds and graphics; obviously these do not fit into the declartive semantics of Prolog and have to be dealt with under the procedural semantics. If you want to execute a Matlab command in an imperative way and see the textual output, use the ??/1 operator, eg

?- ??disp(`hello).

>> hello

The interface works by using the Matlab Engine API, which starts up a Matlab process on the end of a pipe. The Matlab process can be on another machine, and multiple Matlab engines can be started on the same or different machines. Matlab expressions are sent down the pipe and executed. Matlab's textual output comes back through the pipe. In addition, Matlab variables can be transferred directly between the Matlab engine's memory space and SWI's memory space.

See README for further details.

Download as ...

gzipped tar plml-0.1.tar.gz 42 KB

Reference Structural Segmentations

Authors: M. Levy, K. Noland, G. Peeters

Annotations of musical form (verses, choruses etc.) for 60 songs by The Beatles, Britney Spears, Michael Jackson, Madonna, Prince, The Clash, etc.


M. Levy and M. Sandler: Structural Segmentation of Musical Audio by Constrained Clustering. Submitted to IEEE Transactions on Audio, Speech & Language Processing.

zip reference_segmentations.zip 32 KB
tar.gz reference_segmentations.tar.gz 16 KB

Adaptive whitening

"Adaptive whitening" is a process that aims approximately to "whiten" an audio signal by processing FFT frames causally and in real-time. This enables improved real-time onset detection by mitigating against problems caused by varying dynamics and spectral roll-off.

Implementation Copyright 2007: Dan Stowell
License: GNU General Public License


D. Stowell and M. D. Plumbley (2007) Adaptive whitening for improved real-time audio onset detection. In Proceedings of the International Computer Music Conference (ICMC’07), August 2007.
[Download preprint: pdf (450k)]

Download as . . .

SuperCollider plugin See instructions


kdpee - k-d partitioning entropy estimator

A fast estimator for the entropy of multidimensional data distributions. Written in C, can be used from Python, Matlab or Octave.

Implementation Copyright 2008-2010: Dan Stowell
License: GNU General Public License


D. Stowell and M. D. Plumbley, Fast multidimensional entropy estimation by k-d partitioning, IEEE Signal Processing Letters 16 (6), 537–540, June 2009. DOI:10.1109/LSP.2009.2017346

Download here: kdpee is now available on Github


Annotated beatbox data "beatboxset1"

Recordings of fourteen different beatboxers, each with two independent annotations of onset locations and classifications.

Co-ordinated by Dan Stowell. Published under the Creative Commons licence CC-BY-SA-3.0.

All Download files (from archive.org)