Saved in:
Bibliographic Details
Main Authors: Soiledis, Konstantinos, Papakostas, Maximos Kaliakatsos, Makris, Dimos, Tsamis, Konstantinos
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.13404
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909040203792384
author Soiledis, Konstantinos
Papakostas, Maximos Kaliakatsos
Makris, Dimos
Tsamis, Konstantinos
author_facet Soiledis, Konstantinos
Papakostas, Maximos Kaliakatsos
Makris, Dimos
Tsamis, Konstantinos
contents Symbolic-control drum generation requires preserving explicit event timing and dynamics while synthesizing acoustically plausible waveforms. We present Sec2Drum-DAC, a conditional latent-diffusion model for symbolic-to-audio drum rendering. The model conditions on event features sampled in physical time at codec-frame locations and predicts standardized principal-component coordinates of frozen DAC summed-codebook embeddings rather than waveform samples. In the evaluated DAC configuration, 72 principal components capture the observed training-frame summed-latent subspace under the stated SVD threshold, yielding a compact continuous denoising target with a deterministic reconstruction path to the 1024-dimensional DAC latent space before waveform decoding. Across 1,733 held-out four-beat windows, PCA diffusion improves paired spectral and transient metrics over deterministic PCA regression and a symbolic rendering baseline, while direct regression remains stronger on phase-sensitive waveform L1. Auxiliary RVQ cross-entropy improves short-step diffusion on mel error, onset-flux cosine, and waveform L1, with the most favorable trade-offs occurring at 6-25 denoising steps depending on the metric.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13404
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Seconds-Aligned PCA-DAC Latent Diffusion for Symbolic-to-Audio Drum Rendering
Soiledis, Konstantinos
Papakostas, Maximos Kaliakatsos
Makris, Dimos
Tsamis, Konstantinos
Sound
Symbolic-control drum generation requires preserving explicit event timing and dynamics while synthesizing acoustically plausible waveforms. We present Sec2Drum-DAC, a conditional latent-diffusion model for symbolic-to-audio drum rendering. The model conditions on event features sampled in physical time at codec-frame locations and predicts standardized principal-component coordinates of frozen DAC summed-codebook embeddings rather than waveform samples. In the evaluated DAC configuration, 72 principal components capture the observed training-frame summed-latent subspace under the stated SVD threshold, yielding a compact continuous denoising target with a deterministic reconstruction path to the 1024-dimensional DAC latent space before waveform decoding. Across 1,733 held-out four-beat windows, PCA diffusion improves paired spectral and transient metrics over deterministic PCA regression and a symbolic rendering baseline, while direct regression remains stronger on phase-sensitive waveform L1. Auxiliary RVQ cross-entropy improves short-step diffusion on mel error, onset-flux cosine, and waveform L1, with the most favorable trade-offs occurring at 6-25 denoising steps depending on the metric.
title Seconds-Aligned PCA-DAC Latent Diffusion for Symbolic-to-Audio Drum Rendering
topic Sound
url https://arxiv.org/abs/2605.13404