Drum-to-Vocal Percussion Sound Conversion and Its Evaluation Methodology

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nobukawa, Rinka, Kitamura, Makito, Nakamura, Tomohiko, Takamichi, Shinnosuke, Saruwatari, Hiroshi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911166058463232
author Nobukawa, Rinka
Kitamura, Makito
Nakamura, Tomohiko
Takamichi, Shinnosuke
Saruwatari, Hiroshi
author_facet Nobukawa, Rinka
Kitamura, Makito
Nakamura, Tomohiko
Takamichi, Shinnosuke
Saruwatari, Hiroshi
contents This paper defines the novel task of drum-to-vocal percussion (VP) sound conversion. VP imitates percussion instruments through human vocalization and is frequently employed in contemporary a cappella music. It exhibits acoustic properties distinct from speech and singing (e.g., aperiodicity, noisy transients, and the absence of linguistic structure), making conventional speech or singing synthesis methods unsuitable. We thus formulate VP synthesis as a timbre transfer problem from drum sounds, leveraging their rhythmic and timbral correspondence. To support this formulation, we define three requirements for successful conversion: rhythmic fidelity, timbral consistency, and naturalness as VP. We also propose corresponding subjective evaluation criteria. We implement two baseline conversion methods using a neural audio synthesizer, the real-time audio variational autoencoder (RAVE), with and without vector quantization (VQ). Subjective experiments show that both methods produce plausible VP outputs, with the VQ-based RAVE model yielding more consistent conversion.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16862
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Drum-to-Vocal Percussion Sound Conversion and Its Evaluation Methodology
Nobukawa, Rinka
Kitamura, Makito
Nakamura, Tomohiko
Takamichi, Shinnosuke
Saruwatari, Hiroshi
Sound
Audio and Speech Processing
This paper defines the novel task of drum-to-vocal percussion (VP) sound conversion. VP imitates percussion instruments through human vocalization and is frequently employed in contemporary a cappella music. It exhibits acoustic properties distinct from speech and singing (e.g., aperiodicity, noisy transients, and the absence of linguistic structure), making conventional speech or singing synthesis methods unsuitable. We thus formulate VP synthesis as a timbre transfer problem from drum sounds, leveraging their rhythmic and timbral correspondence. To support this formulation, we define three requirements for successful conversion: rhythmic fidelity, timbral consistency, and naturalness as VP. We also propose corresponding subjective evaluation criteria. We implement two baseline conversion methods using a neural audio synthesizer, the real-time audio variational autoencoder (RAVE), with and without vector quantization (VQ). Subjective experiments show that both methods produce plausible VP outputs, with the VQ-based RAVE model yielding more consistent conversion.
title Drum-to-Vocal Percussion Sound Conversion and Its Evaluation Methodology
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2509.16862