Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lee, Junwon, Tailleur, Modan, Heller, Laurie M., Choi, Keunwoo, Lagrange, Mathieu, McFee, Brian, Imoto, Keisuke, Okamoto, Yuki
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917813074001920
author Lee, Junwon
Tailleur, Modan
Heller, Laurie M.
Choi, Keunwoo
Lagrange, Mathieu
McFee, Brian
Imoto, Keisuke
Okamoto, Yuki
author_facet Lee, Junwon
Tailleur, Modan
Heller, Laurie M.
Choi, Keunwoo
Lagrange, Mathieu
McFee, Brian
Imoto, Keisuke
Okamoto, Yuki
contents Despite significant advancements in neural text-to-audio generation, challenges persist in controllability and evaluation. This paper addresses these issues through the Sound Scene Synthesis challenge held as part of the Detection and Classification of Acoustic Scenes and Events 2024. We present an evaluation protocol combining objective metric, namely Fréchet Audio Distance, with perceptual assessments, utilizing a structured prompt format to enable diverse captions and effective evaluation. Our analysis reveals varying performance across sound categories and model architectures, with larger models generally excelling but innovative lightweight approaches also showing promise. The strong correlation between objective metrics and human ratings validates our evaluation approach. We discuss outcomes in terms of audio quality, controllability, and architectural considerations for text-to-audio synthesizers, providing direction for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17589
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation
Lee, Junwon
Tailleur, Modan
Heller, Laurie M.
Choi, Keunwoo
Lagrange, Mathieu
McFee, Brian
Imoto, Keisuke
Okamoto, Yuki
Sound
Artificial Intelligence
Machine Learning
Multimedia
Audio and Speech Processing
Despite significant advancements in neural text-to-audio generation, challenges persist in controllability and evaluation. This paper addresses these issues through the Sound Scene Synthesis challenge held as part of the Detection and Classification of Acoustic Scenes and Events 2024. We present an evaluation protocol combining objective metric, namely Fréchet Audio Distance, with perceptual assessments, utilizing a structured prompt format to enable diverse captions and effective evaluation. Our analysis reveals varying performance across sound categories and model architectures, with larger models generally excelling but innovative lightweight approaches also showing promise. The strong correlation between objective metrics and human ratings validates our evaluation approach. We discuss outcomes in terms of audio quality, controllability, and architectural considerations for text-to-audio synthesizers, providing direction for future research.
title Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation
topic Sound
Artificial Intelligence
Machine Learning
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2410.17589