Timeline for Choosing the best measure for machine learning on a Spectrogram
Current License: CC BY-SA 3.0
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 22, 2014 at 3:20 | comment | added | Aakash Anuj | I am trying to develop a classifier for Indian Taals, for which I would be focusing only on the Tabla. Now once a extract a period of the tala, I want to develop some feature vectors for a Tala. I am not sure what they should be. Could you help me with that? As of now, what I am planning to do is to find the beats of the Tala by beat tracking, or the onsets and take the median of the spectrogram values at the beat time to be my feature vector. Do you have any other ideas? Also, you mentioned about bayan/dayan. Using them would also e useful. Could you point me to some library and ideas? Thanks | |
| Oct 21, 2014 at 22:07 | history | edited | pichenettes | CC BY-SA 3.0 |
deleted 6 characters in body
|
| Oct 21, 2014 at 16:46 | history | answered | pichenettes | CC BY-SA 3.0 |