News for hackers. Stuff that matters.
Re:Music Language Modeling with Recurrent Neural Networks by varelse on Friday April 01, 2016 @10:02AM (#11404799)
Both of the pieces at the top of the article sound like off-key broken record renditions of the main refrain of "Jesu, Joy of Man's Desiring" to me. It's like the RNN cannot hold enough state to express the structure of a real musical piece and it just emits riffs here and there of main themes from its training set.

What would be somewhat impressive is if it spontaneously figured out the note sequence I hear from observing its re-expression in bits and pieces from various jigs and folk pieces in its training set, kind of like this:

https://www.youtube.com/watch?v=XPLp_gInC-o

Re:Music Language Modeling with Recurrent Neural Networks by pitchka on Friday April 01, 2016 @11:10AM (#11405335)
LSTM can hold as much state as you want.

It would make more sense to force the leitmotif and generate the rest of the song instead of generating from a random note.