Chord-conditioned Melody and Bass Generation
By: Alexandra C Salem, Mohammad Shokri, Johanna Devaney
Potential Business Impact:
Makes music sound better by following chords.
We evaluate five Transformer-based strategies for chord-conditioned melody and bass generation using a set of music theory-motivated metrics capturing pitch content, pitch interval size, and chord tone usage. The evaluated models include (1) no chord conditioning, (2) independent line chord-conditioned generation, (3) bass-first chord-conditioned generation, (4) melody-first chord-conditioned generation, and (5) chord-conditioned co-generation. We show that chord-conditioning improves the replication of stylistic pitch content and chord tone usage characteristics, particularly for the bass-first model.
Similar Papers
Incorporating Structure and Chord Constraints in Symbolic Transformer-based Melodic Harmonization
Sound
Makes music generators follow your chord ideas.
Training chord recognition models on artificially generated audio
Sound
Makes music AI learn chords from fake songs.
A Controllable Perceptual Feature Generative Model for Melody Harmonization via Conditional Variational Autoencoder
Sound
Creates new music with feeling and style.