首页 > AI前沿 > SPDMX: Large-Scale Open Stem Audio From Symbolic Music

SPDMX: Large-Scale Open Stem Audio From Symbolic Music

arXiv机器学习 2026-11-06 16:14 17 阅读 查看原文

Large public datasets have driven recent progress in machine learning, from text and vision to speech and general audio.

Music remains an outlier, as copyright blocks redistribution of training audio, while many modern tasks need individual stems rather than mixtures.

Limitations of existing resources

Existing multitrack resources trade off realism, scale, and licensing, while synthetic alternatives rely on proprietary VSTs or naive open rendering that yields weak stems.

Introducing SPDMX

We introduce SPDMX, a listening-guided rendering of public-domain PDMX scores into an openly-licensed stem corpus with aligned scores and an open render pipeline:

  • $253{,}982$ songs
  • $490{,}159$ mono stems
  • $5{,}469$ song-hours at $44.1$ kHz under CC BY 4.0, with paired MIDI and identifiers linking to PDMX metadata

Multitrack supervision

$88{,}403$ songs ($34.8\%$; $2{,}734$ song-hours) provide multitrack supervision.

Significance and scope

To our knowledge, this is the largest openly-licensed synthetic multitrack subset by song-hours, enabling:

  • source separation
  • stem-conditioned synthesis
  • MIDI-to-audio
  • transcription
  • joint symbolic-audio modeling

Release and reuse

We release the corpus, metadata, and open pipeline for reuse on other symbolic collections.

Demos and experimental notes are on the project page.