SLIDE 1
Computer-Generated Sound
Final Project
Mu-Heng Yang mhyang@Stanford.edu
Computer-Generated Sound
Final Project
Mu-Heng Yang mhyang@Stanford.edu
Computer-Generated Sound Final Project Mu-Heng Yang - - PowerPoint PPT Presentation
Computer-Generated Sound Final Project Mu-Heng Yang - - PowerPoint PPT Presentation
Computer-Generated Sound Final Project Mu-Heng Yang mhyang@Stanford.edu Music Computer-Generated Sound Final Project Mu-Heng Yang mhyang@Stanford.edu Algorithmic Composition Mu-Heng Yang mhyang@Stanford.edu StkInstrument Parameter
SLIDE 2
SLIDE 3
Algorithmic Composition
Mu-Heng Yang mhyang@Stanford.edu
SLIDE 4
StkInstrument
Parameter tuning for timbre and volume balance Melody Line (Rhodey) Bowed (Chord Progression) Bass Line (BandedWG) Key Root (VoicForm) Hihat (Shakers) Bass Drum (BandedWG) Snare (Shakers)
SLIDE 5
Composition Concept
Stable v.s. Random Add some random variables in my software. It decides when the notes are played and which notes to play It decides when the drums are played and which drums to play
SLIDE 6
Song Structure
Song structure makes music different from sound Verse Chorus Bridge Chorus Use random variable to make verse filled with less notes Enjoy the music (https://ccrma.stanford.edu/~mhyang/220a/fp/fp.wav)
SLIDE 7
Machine Learning
Crawled online for thousands of songs in MIDI format Process them into useful information
key, melody, chord, root, genre, instrument, artist, verse/chorus…
Develop algorithm to predict the next note given the current melody lin Enjoy the music (https://ccrma.stanford.edu/~mhyang/220a/fp/fp-ml.wav)
SLIDE 8
Conclusion & Future Work
It now sounds more like human-composed melody
instead of monkey randomly tapping keyboard.
It can easily scale-up or adjust to user-input
Compose with requested key, genre, instruments,
artist style, song structure, and emotion.
I’ve implemented automatic accompaniment
system using deep learning and would love to import it into this project!
SLIDE 9