"Transfer learning for music classification and regression tasks" by Keunwoo Choi, George Fazekas, Mark Sandler, and Kyunghyu Cho. This paper received Best paper award in ISMIR 2017.
Paper:
https://arxiv.org/abs/1703.09179
Video:
https://www.youtube.com/watch?v=kKzjM58LgVw&feature=youtu.be
23. Convnet feature
How musical is MFCCs?
• For musical tasks, adding MFCCs to convnet hurts
• For the non-musical task, it was better!
• ..which might mean...
MFCC’s
musical aspect
MFCC’s
non-musical aspect
“to this extent.”
“maybe no more than convnet feature”
27. Conclusions
• Exhaustive still efficient multi-layer convnet feature
• Different layer, different meaning
• Music tagging as a source task seems versatile
• Codes/weights are out there!
28. Transfer learning
Keunwoo.Choi
@qmul.ac.uk
for music classification and regression tasks
György Fazekas, Mark Sandler, Kyunghyun Cho
The 18th International Society of Music Information Retrieval Conference, Suzhou, China, 2017
29. Links
My blog | A blog post on this | Paper! | Codes and weights
@keunwoochoi