Metraipolis › archive › dc_d4bfae4a67fb

MiDiff: MIDI-Conditioned Diffusion Models for Drum Audio Enhancement — arXiv:2610.38619

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.38619
License (as archived): CC0-1.0
Archived: 2026-11-01T03:01:06.029Z
SHA-256 of the archived text: baa1102132098e8a7de9f56854c2de0455538afbcbf3ade92ec110b5b75e1349
Stable URL of this page: https://metraipolis.com/documento/dc_d4bfae4a67fb

How to cite

MiDiff: MIDI-Conditioned Diffusion Models for Drum Audio Enhancement — arXiv:2610.38619 — arXiv (en), https://arxiv.org/abs/2610.38619 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d4bfae4a67fb (Metraipolis archive dc_d4bfae4a67fb, sha256 baa1102132098e8a7de9f56854c2de0455538afbcbf3ade92ec110b5b75e1349)

BibTeX

@misc{dcd4bfae4a67fb,
  title = {MiDiff: MIDI-Conditioned Diffusion Models for Drum Audio Enhancement — arXiv:2610.38619},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38619},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d4bfae4a67fb; sha256 baa1102132098e8a7de9f56854c2de0455538afbcbf3ade92ec110b5b75e1349},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38619. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Bridging the semantic gap between perfect symbolic musical structure and severely degraded acoustic signals offers a powerful paradigm for high-fidelity audio restoration. We introduce MiDiff, a diffusion-based generative model for drum audio enhancement that conditions the reverse process on temporally aligned Musical Instrument Digital Interface (MIDI) piano rolls. We extend the Score-Based Generative Models for Speech Enhancement (SGMSE) framework in the complex Short-Time Fourier Transform (STFT) domain by integrating a pretrained MIDI encoder, multi-scale temporal alignment, and three complementary conditioning strategies: early injection, Feature-wise Linear Modulation (FiLM), and cross-attention. We further show that providing the same piano roll only through classifier guidance, driven by an Automatic Drum Transcription (ADT) model on the audio-only score, yields no measurable gain: the symbolic prior is effective when it conditions the score network. To relax the requirement for ground-truth MIDI at inference, we further propose a hybrid reverse schedule that transcribes the diffusion state online with the same noise-aware ADT network and hands over from the audio-only score to MiDiff at a tunable switch time, cutting test FAD by 47% relative to the audio-only baseline without any symbolic input (switch time selected on the test set). We train our model on the StemGMD dataset using a non-additive degradation pipeline that simulates room reverberation with echo, electret capsule frequency response, and soft-clipping saturation with noise. MiDiff substantially outperforms the SGMSE baseline in terms of Fréchet Audio Distance (FAD) on both the validation and held-out test sets. Ablation studies demonstrate that combining all three conditioning strategies yields superior performance and that authentic MIDI velocity dynamics are critical for effective symbolic conditioning.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv eess.SP, nuovi lavori del giorno).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2610.38619 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-01T02:25:45.630Z dalla pagina https://arxiv.org/list/eess.SP/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).