Saved in:
Bibliographic Details
Main Authors: Zhang, Huan, Liang, Jinhua, Phan, Huy, Wang, Wenwu, Benetos, Emmanouil
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.21815
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916715322933248
author Zhang, Huan
Liang, Jinhua
Phan, Huy
Wang, Wenwu
Benetos, Emmanouil
author_facet Zhang, Huan
Liang, Jinhua
Phan, Huy
Wang, Wenwu
Benetos, Emmanouil
contents Evaluating generative models remains a fundamental challenge, particularly when the goal is to reflect human preferences. In this paper, we use music generation as a case study to investigate the gap between automatic evaluation metrics and human preferences. We conduct comparative experiments across five state-of-the-art music generation approaches, assessing both perceptual quality and distributional similarity to human-composed music. Specifically, we evaluate synthesis music from various perceptual dimensions and examine reference-based metrics such as Mauve Audio Divergence (MAD) and Kernel Audio Distance (KAD). Our findings reveal significant inconsistencies across the different metrics, highlighting the limitation of the current evaluation practice. To support further research, we release a benchmark dataset comprising samples from multiple models. This study provides a broader perspective on the alignment of human preference in generative modeling, advocating for more human-centered evaluation strategies across domains.
format Preprint
id arxiv_https___arxiv_org_abs_2504_21815
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Aesthetics to Human Preferences: Comparative Perspectives of Evaluating Text-to-Music Systems
Zhang, Huan
Liang, Jinhua
Phan, Huy
Wang, Wenwu
Benetos, Emmanouil
Audio and Speech Processing
Evaluating generative models remains a fundamental challenge, particularly when the goal is to reflect human preferences. In this paper, we use music generation as a case study to investigate the gap between automatic evaluation metrics and human preferences. We conduct comparative experiments across five state-of-the-art music generation approaches, assessing both perceptual quality and distributional similarity to human-composed music. Specifically, we evaluate synthesis music from various perceptual dimensions and examine reference-based metrics such as Mauve Audio Divergence (MAD) and Kernel Audio Distance (KAD). Our findings reveal significant inconsistencies across the different metrics, highlighting the limitation of the current evaluation practice. To support further research, we release a benchmark dataset comprising samples from multiple models. This study provides a broader perspective on the alignment of human preference in generative modeling, advocating for more human-centered evaluation strategies across domains.
title From Aesthetics to Human Preferences: Comparative Perspectives of Evaluating Text-to-Music Systems
topic Audio and Speech Processing
url https://arxiv.org/abs/2504.21815