Synthesis and editing of multi-instrument audio mixtures using scalar-quantised latents with MIDI Span conditioning
SpanSynth-Edit is introduced, a flow-matching model for MIDI-guided synthesis and editing of multi-instrument audio mixtures using low-frame-rate scalar-quantised latents using low-frame-rate scalar-quantised latents.
Sungkyun Chang, K. Bhandari, Simon Dixon et al.
· 0 citations