Neural Network Drum Track Composition

1
Neural Network Drum Track Composition

• Dan Smith

2
Goal

• Develop a neural net which can be trained to
  produce drum tracks given a few starting beats.

3
Previous work

• Michael Mozer Neural Network Music composition
  by prediction
• Adam Guetz and Tony Lee Neural Network Music
  Composition

4
Network

• Each note is presented to network, the network
  predicts next note.
• Training mode
• At each note, error is calculated based on next
  note
• Weights are updated
• Simulation mode
• Next note is fed back into network

5
Network architecture
Neural Network
Next note
Note selector
Context
6
Note representation

• Note is respresented at duration and instruments
• Six instruments snare, tom1, tom2, cymbal,
  hi-hat, bass.

7
Instrument Representation

• Instruments are represented in binary, 1 means
  the instrument is being played, 0 means it is not
• Vector is (snare, tom1, tom2, cymbal, hi-hat,
  bass)

8
Duration representation

• Time is divided into ticks. Each tick represents
  1/12 of a beat.
• Eighth note 6 ticks
• Eighth note triplet 4 ticks
• Note is represented by elapsed time, as well as
  (elapsed time mod 4) and (elapsed time mod 3)

9
Why?

• Eighth notes sixteenth notes mod 3
• 3 mod 3 0
• 6 mod 3 0
• Eight note triplets quarter note triplets mod 4
• 4 mod 4 0
• 8 mod 4 0

10
Duration(cont)

• Each mod is represented by a 1 hot code
• Eg 6 mod 4 2 0100
• 6 mod 3 0 001

11
Total representation

• 14 until vector
• (duration, mod4 (4 inputs), mod3 (3 inputs),
  snare, tom1, tom2, cymbal, hi-bat, bass)

12
Converting Output to Next Note

• Duration is distributed, must pick real duration
• Pick duration vector closest to the duration
  produced by the network

13
Results

• Network learned simple patterns without repeated
  note (analogous to previous work)
• Network learned patterns with repeated notes
• Did not generalize well

14
Future suggestions

• Work on generalization
• Problem with context resetting
• Try top down production Method

15
References

• Michael Mozer Neural network music composition
  by prediction
• http//www.cs.colorado.edu/mozer/papers/music.htm
  l
• Tony Lee and Adam Guetz Neural Network Music
  compostion
• http//www3.hmc.edu/anlee/cs152/