Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Zhe, Özer, Yigitcan, Yamagishi, Junichi
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.12389
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918445837189120
author Zhang, Zhe
Özer, Yigitcan
Yamagishi, Junichi
author_facet Zhang, Zhe
Özer, Yigitcan
Yamagishi, Junichi
contents Speech audio in the wild is often processed by post-production effects, but existing speech datasets rarely provide precise annotations of effects and parameters, limiting systematic study. We introduce VoxEffects, a speech audio effects dataset that pairs produced speech with exact effect-chain supervision at multiple granularities. VoxEffects supports speech-oriented audio effect identification: given a produced waveform, infer which effects are present and how they are applied. Built from minimally edited clean speech, it provides an extensible rendering pipeline for both offline synthesis and on-the-fly rendering for efficient training and evaluation. The audio effect identification benchmark includes effect presence detection, preset classification, and intensity prediction, with a robustness protocol covering capture-side and platform-side degradations. We provide an AudioMAE-based multi-task baseline and analyses of domain shift, robustness, input duration, and gender fairness.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12389
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VoxEffects: A Speech-Oriented Audio Effects Dataset and Benchmark
Zhang, Zhe
Özer, Yigitcan
Yamagishi, Junichi
Audio and Speech Processing
Speech audio in the wild is often processed by post-production effects, but existing speech datasets rarely provide precise annotations of effects and parameters, limiting systematic study. We introduce VoxEffects, a speech audio effects dataset that pairs produced speech with exact effect-chain supervision at multiple granularities. VoxEffects supports speech-oriented audio effect identification: given a produced waveform, infer which effects are present and how they are applied. Built from minimally edited clean speech, it provides an extensible rendering pipeline for both offline synthesis and on-the-fly rendering for efficient training and evaluation. The audio effect identification benchmark includes effect presence detection, preset classification, and intensity prediction, with a robustness protocol covering capture-side and platform-side degradations. We provide an AudioMAE-based multi-task baseline and analyses of domain shift, robustness, input duration, and gender fairness.
title VoxEffects: A Speech-Oriented Audio Effects Dataset and Benchmark
topic Audio and Speech Processing
url https://arxiv.org/abs/2604.12389