[PD] Machine learning and sound ?

[Andy Farnell]

We use a combo of modified mfcc and k-means at Mogees to get
over 95% accuracy of percussion sounds.

To add a few words to what Jamie says, on what I've learned
about working in this domain;

1) It really helps to understand your problem and the possible
ways it can be assisted by ML. Is real-time training needed?
Or do you have lots of off-line time for your ML to "think"?

2) How many training examples will you use, and where will
they come from? How diverse/typical are they?

3) Will you supervise the ML (give clues to steer it) or allow
it to make up its own mind about classes/clusters (unsupervised)?

4) What kind of output are you hoping for, prediction, regression
a definite match, or a set of probabilities, or a vector of
distances from possible matches?

5) How does signal time figure in your problem? Do you want
pitch or duration independence?

6) How will you segment and arrange data relative to block 
boundaries and the size of any transform (fft/wavelet)? Tiny
variations can lead to big differences. Will you zero pad
to remove junk? Will you use windows/envelopes to soften
edges? 

7) What do you know about the source and structure of the sounds
to be processed? Are they;

   i)  'Samples' with identical byte patterns?
  ii)  Never heard before?
 iii)  Known structure, segments, chunks. eg. speech?
  iv)  Highly structured 'samples', hashable, eg. MIR
   v)  Largely similar, seeking a specific structural variation?
  vi)  Transient, sustained, harmonic? Or complex evolution?
  
Machine learning right now is a set of quite specialised building
blocks. Each of the above shapes of problem may suggest substantially
different choices of components and configuration.

Pre-processing, like shelf EQ and compression can make a _huge_
difference to the quality and reliability of results.

I havent used the ml.lib before , but the idea of having a
load of ML components to play with in Pd is really attractive
and I'm sure you will have tons of fun!

cheers,
Andy
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 230 bytes
Desc: Digital signature
URL: <http://lists.puredata.info/pipermail/pd-list/attachments/20160724/9be40060/attachment.sig>