1 / 15

Neural Network Drum Track Composition

Neural Network Drum Track Composition. Dan Smith. Goal. Develop a neural net which can be trained to produce drum tracks given a few starting beats. Previous work. Michael Mozer – Neural Network Music composition by prediction Adam Guetz and Tony Lee – Neural Network Music Composition.

farrah
Download Presentation

Neural Network Drum Track Composition

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  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.html • Tony Lee and Adam Guetz – Neural Network Music compostion • http://www3.hmc.edu/~anlee/cs152/

More Related