This video demonstrates how to use a neural network to distinguish between oboe and trombone timbre using the FluCoMa Toolbox in SuperCollider.
0:16 Demo
0:25 Theory
3:30 Creating Training and Testing Sets
7:18 MFCC Analysis
11:44 Adding Analyses to a FluidDataSet
19:52 Training the Neural Network
22:02 Making Predictions (Testing the Neural Network)
23:47 Making Predictions on the server
28:43 Loudness Threshold Gating Predictions
For more information about the attributes of FluidMLPClassifier, visit https://learn.flucoma.org/reference/mlpclassifier/
Find the completed code here:
https://learn.flucoma.org/examples/classification-video-demo.scd
The Fluid Corpus Manipulation Toolbox (FluCoMa) is a software extension that enables programmatic sound bank mining with machine listening and machine learning within Max, SuperCollider, and Pure Data.
Website: https://www.flucoma.org/
Download: https://www.flucoma.org/download/
Discourse: https://discourse.flucoma.org/
Max: https://cycling74.com/
SuperCollider: https://supercollider.github.io/
Pure Data: https://puredata.info/
#neuralnetworks #machinelearning #supercollider #flucoma
