Talk:Music representations: Challenges
From MIReS
(Difference between revisions)
(Comment provided by usageoufalf - via ArticleComments extension) |
|||
Line 18: | Line 18: | ||
Posted by '''''[[User:ArthurF|ArthurF]]''''' on 17:01, 31 October 2012 (UTC) | Posted by '''''[[User:ArthurF|ArthurF]]''''' on 17:01, 31 October 2012 (UTC) | ||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
- | |||
</div> | </div> |
Latest revision as of 22:48, 25 March 2013
Comments on Music representations: Challenges
Automatic feature learning looks like a challenge for music representation to me:
"Moving Beyond Feature Design: Deep Architectures and Automatic Feature Learning in Music Informatics" by Eric J. Humphrey, Juan P. Bello, Yann LeCun
http://ismir2012.ismir.net/event/papers/403-ismir-2012.pdf
See also the corresponding Late-Breaking Session: (Deep) Feature Learning
https://ismir2012.wikispaces.com/Wrap-up+Feature+Learning
Posted by ArthurF on 17:01, 31 October 2012 (UTC)