MnM

Mapping is not Music

MnM is a set of Max/MSP externals based on FTMlib providing a unified framework for various techniques of classification, recognition and mapping for motion capture data, sound and music.

Features currently implemented in MnM include:

• Hidden Markov Models, see for example Gesture Follower
• Principal Components Analysis
• Singular Value Decomposition, LU and QR decompositions
• Non-negative Matrix Factorization and sparse decomposition
• multi-dimensionnal M to N mapping based on examples
• Multi-dimensioannal autocorrelation
• Matrix/Vector Statistics (min, max, mean, std, histogram, mahalanobis distance)

The MnM package is released within the FTM distributions.

Publications

• NIME 2006 paper on MnM (PDF)