There is a need to classify an audio stream in real-time - using one from thousands of the defined classes. Up to 5000 classes potentially.
What's the best machine learning algorithm for this task?
DTW? HMM? SVM? Some specific DSP algorithms?
$\begingroup$
$\endgroup$
4
-
$\begingroup$ Anything that doesn't require extracting expensive features; something that works with FFTs and MFCCs, such as a modern neural network should be fine. The training complexity is not an issue in your case. $\endgroup$– EmreCommented Jul 1, 2016 at 20:19
-
$\begingroup$ Could give some example of the classes? Is your problem similar to speech recognition? $\endgroup$– WilliamCommented Jul 1, 2016 at 20:24
-
$\begingroup$ Yes, similar to speech recognition, but discovering such things as "car engine", "scream", "human steps", "dog barks" etc. $\endgroup$– Oleg PuzanovCommented Jul 1, 2016 at 20:32
-
$\begingroup$ SVM should work too. $\endgroup$– n1tkCommented Jul 3, 2016 at 4:41
Add a comment
|