Dempster, P., Laird, N. M., and Rubin, D. B. .
Maximum likelihood from incomplete data using the EM algorithm.
Journal of the Royal Society of Statistics, vol. 39(1): pp. 1--38.
- Original article coining the term of Expectation Maximisation algorithm. I could not find a copy of the article.
Duda, R. O. and Hart, P. E. .
Pattern Classification and Scene Analysis.
John Wiley and Sons, Inc.
- Very useful ressource. Quite theoretical but gives a very thorough introduction to pattern recognition. The chapters on Mixed Distributions and Clustering were particularly helpful for this presentation.
Eggink, J. and Brown, G. J. .
A missing feature approach to instrument identification.
In Audio Speech and Sound Processing, 2003, Proceedings of the International
- An interesting approach for polyphonic instrument identification. Uses a fundamental estimation algorithm that is worth researching more in depth: it uses "fundamental sieves" (a fundamental candidate accompanied by its harmonic series of overtones) and determines fundamental candidates.
Marolt, M. .
Gaussian mixture models for extraction of melodic lines from audio recordings.
In Proceedings of the 2004 International Conference on Music Information
- Quite recent article trying to extract high level information out of polyphonic audio. One might question the unsupervised-ness of the approach (because of the constraints imposed during training). It would be worth checking if they have managed to go on with this research. Especially, if they have managed to identify relevant timbre features left out so far.
Marques, J. and Moreno, P. J. .
A study of musical instrument classification using gaussian mixture models and
support vector machines.
Tech. rep., COMPAQ, Cambridge Research Laboratory.
- Although the results are not great at first glance, the article is very clearly written and was of great help for this presentation. It allowed me to understand how GMM could be used to instrument classification.
Moon, T. K. .
The expectation-maximization algorithm.
IEEE Signal Processing Magazine: pp. 47--61.
- Good "vulgarization" article on the EM algorithm, with a list of applications, basic examples to understand the main concepts.