Synthesis and editing of multi-instrument audio mixtures using scalar-quantised latents with MIDI Span conditioning

2026-09-21

AI Summary

该研究提出SpanSynth-Edit模型，利用MIDI Span条件和低帧率标量量化潜变量，支持多乐器音频混合的合成与编辑。

Abstract

Music creation often involves iterative refinement, changing selected musical details while retaining the rest. To support such refinement, we introduce SpanSynth-Edit, a flow-matching model for MIDI-guided synthesis and editing of multi-instrument audio mixtures using low-frame-rate scalar-quantised latents. MIDI Span encodes instrument-labelled note lifecycles as unordered event sets with continuous-valued attributes and pools each set into one conditioning vector per audio-latent frame. The model uses contextual audio for instrument-specific timbre guidance and supports editing by resynthesising the target region from revised MIDI. Experiments on single- and multi-instrument benchmarks show competitive performance and demonstrate within-frame onset control. We also discuss limitations of transcription-based note-adherence evaluation.

Problem

• MIDI-guided synthesis
• multi-instrument audio mixtures
• iterative refinement

Innovation

• flow-matching model
• MIDI-guided synthesis
• scalar-quantised latents
• multi-instrument audio mixtures
• contextual audio