From ftm
Jump to: navigation, search
(features)
(Mapping is not Music)
 
(21 intermediate revisions by 2 users not shown)
Line 1: Line 1:
''Mapping is Not Music''
+
== 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.
  
== about ==
+
Features currently implemented in MnM include:
[[MnM]] is a set of Max/MSP externals based on [[FTM]] providing a unified framework for various techniques of classification, recognition and mapping for motion capture data, sound and music.
+
* Hidden Markov Models, see for example [[Gesture Follower]]
 
 
== features ==
 
* Hidden Markov Models
 
 
* Principal Components Analysis
 
* Principal Components Analysis
* Singular Value Decomposition
+
* Singular Value Decomposition, LU and QR decompositions
 
* Non-negative Matrix Factorization and sparse decomposition
 
* Non-negative Matrix Factorization and sparse decomposition
 
* multi-dimensionnal M to N mapping based on examples
 
* multi-dimensionnal M to N mapping based on examples
Line 13: Line 11:
 
* Matrix/Vector Statistics (min, max, mean, std, histogram, mahalanobis distance)
 
* Matrix/Vector Statistics (min, max, mean, std, histogram, mahalanobis distance)
  
== papers ==
+
The MnM package is released within the [[Download | FTM distributions]].
[http://recherche.ircam.fr/equipes/temps-reel/articles/mnm.nime05.pdf download PDF of NIME 2005 paper on MnM]
 
  
----
+
== Publications ==
The [[MnM]] object set is released within the [[FTM]] distribution..
+
{{:MnM Publications}}

Latest revision as of 22:36, 10 February 2008

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