|
| EPSRC Reference: |
GR/R54620/01 |
| Title: |
Automatic Polyphonic Music Transcription Using Multiple Cause Models and Independant Component Analysis. |
| Principal Investigator: |
Professor M Plumbley |
| Other Investigators: |
|
| Researcher Co-investigator: |
|
| Project Partner: |
|
| Department: |
Sch of Electronic Eng & Computer Science |
| Organisation: |
Queen Mary, University of London |
| Scheme: |
Standard Research |
| Starts: |
01 January 2002 |
Ends: |
30 June 2004 |
Value (£): |
124,946
|
| EPSRC Research Topic Classifications: |
| Digital Signal Processing |
Multimedia |
| Neural Computing |
|
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary |
We aim to develop a methodology for automatic transcription of polyphonic music from audio. Our approach is based on the use of adaptive learning systems, specifically multiple-cause model neural networks and independent component analysis (ICA), as data-driven analysis of time-frequency representations. We will use these models to learn note shapes from musical data, rather than relying on experimentally measured characteristics of the human auditory system.
In this project we will concentrate on these bottom-up methods, to focus on exactly how much can be extracted from the input data alone, and to complement other work on top-down and heuristic methods taking place in our Lab and elsewhere.
As part of this work, we will need to tackle a number of challenges from real-world audio data, such as time-varying spectral shape of instruments, reverberation, nonlinear behaviour of instruments, and noise in audio recordings. To this end, we will use a number of recent developments in multiple cause models and ICA, such as sparse coding, noisy ICA, and nonlinear ICA, and will extend our initial instantaneous analysis to include temporal information.
|
| Final Report Summary |
Automatic music transcription, the task of automatically extracting the notes in a piece of music, is particularly difficult for polyphonic music, where more than one note is played at a time. Many approaches have previously been tried using knowledge about musical audio or human hearing. The aim of this project has been to develop new fundamental methods to tackle the automatic music transcription problem, that learn the characteristics of notes from the data, at the same time as extracting the notes themselves. These techniques are based on assumptions that (a) the notes are relatively independent from each other, and (b) that the occurrence of notes is sparse, i.e. that few notes are present at any one time. The techniques we have been using are known as independent component analysis (ICA) and sparse coding.
In the project, we developed a new method for automatic music transcription based on these techniques. We found that notes were typically represented by groups of a handful of vectors each, representing the way the frequency spectrum of the note changed as the note sounded. We also developed new non-negative ICA and non-negative sparse coding techniques, taking advantage of the fact that note activities must be positive or zero, and investigated a new shift-invariant sparse coding method to learn the waveforms directly. We also used ICA to find independent basis vectors to represent music and speech, and developed a method to visualize the relationships between these basis vectors. The visualization for music is reminiscent of the idea of a circle of fifths familiar to musicians. We also developed an onset detection method based on ICA, giving a surprise signal which is high when a new note begins.
In the future, techniques like this could be used to analyse the content of the huge collections of music in digital formats like MP3. Using this analysis, it would be possible to search through personal or commercial collections of music just as easily as an internet search engine can be used today.
|
| Further Information: |
http://www.elec.qmul.ac.uk/research/projects/epsrc_grr54620_music_trans.html |
| Organisation Website: |
http://www.qmul.ac.uk |
|
|