Guardado en:
Detalles Bibliográficos
Autores principales: Soiledis, Konstantinos, Kaliakatsos-Papakostas, Maximos, Makris, Dimos, Tsamis, Konstantinos
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.10281
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918494174445568
author Soiledis, Konstantinos
Kaliakatsos-Papakostas, Maximos
Makris, Dimos
Tsamis, Konstantinos
author_facet Soiledis, Konstantinos
Kaliakatsos-Papakostas, Maximos
Makris, Dimos
Tsamis, Konstantinos
contents Generating realistic drum audio directly from symbolic representations is a challenging task at the intersection of music perception and machine learning. We propose a system that transforms an expressive drum grid, a time-aligned MIDI representation with microtiming and velocity information, into drum audio by predicting discrete codes of a neural audio codec. Our approach uses a Transformer-based model to map the drum grid input to a sequence of codec tokens, which are then converted to waveform audio via a pre-trained codec decoder. We experiment with multiple state-of-the-art neural codecs, namely EnCodec, DAC, and X-Codec, to assess how the choice of audio representation impacts the quality of the generated drums. The system is trained and evaluated on the Expanded Groove MIDI Dataset, E-GMD, a large collection of human drum performances with paired MIDI and audio. We evaluate the fidelity and musical alignment of the generated audio using objective metrics. Overall, our results establish codec-token prediction as an effective route for drum grid-to-audio generation and provide practical insights into selecting audio tokenizers for percussive synthesis.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10281
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Drum Synthesis from Expressive Drum Grids via Neural Audio Codecs
Soiledis, Konstantinos
Kaliakatsos-Papakostas, Maximos
Makris, Dimos
Tsamis, Konstantinos
Sound
Artificial Intelligence
Generating realistic drum audio directly from symbolic representations is a challenging task at the intersection of music perception and machine learning. We propose a system that transforms an expressive drum grid, a time-aligned MIDI representation with microtiming and velocity information, into drum audio by predicting discrete codes of a neural audio codec. Our approach uses a Transformer-based model to map the drum grid input to a sequence of codec tokens, which are then converted to waveform audio via a pre-trained codec decoder. We experiment with multiple state-of-the-art neural codecs, namely EnCodec, DAC, and X-Codec, to assess how the choice of audio representation impacts the quality of the generated drums. The system is trained and evaluated on the Expanded Groove MIDI Dataset, E-GMD, a large collection of human drum performances with paired MIDI and audio. We evaluate the fidelity and musical alignment of the generated audio using objective metrics. Overall, our results establish codec-token prediction as an effective route for drum grid-to-audio generation and provide practical insights into selecting audio tokenizers for percussive synthesis.
title Drum Synthesis from Expressive Drum Grids via Neural Audio Codecs
topic Sound
Artificial Intelligence
url https://arxiv.org/abs/2605.10281