Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Chien-Chun, Huang, Kuan-Tang, Yang, Cheng-Yeh, Lee, Hung-Shin, Wang, Hsin-Min, Chen, Berlin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.08957
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912534419734528
author Wang, Chien-Chun
Huang, Kuan-Tang
Yang, Cheng-Yeh
Lee, Hung-Shin
Wang, Hsin-Min
Chen, Berlin
author_facet Wang, Chien-Chun
Huang, Kuan-Tang
Yang, Cheng-Yeh
Lee, Hung-Shin
Wang, Hsin-Min
Chen, Berlin
contents Evaluating audio generation systems, including text-to-music (TTM), text-to-speech (TTS), and text-to-audio (TTA), remains challenging due to the subjective and multi-dimensional nature of human perception. Existing methods treat mean opinion score (MOS) prediction as a regression problem, but standard regression losses overlook the relativity of perceptual judgments. To address this limitation, we introduce QAMRO, a novel Quality-aware Adaptive Margin Ranking Optimization framework that seamlessly integrates regression objectives from different perspectives, aiming to highlight perceptual differences and prioritize accurate ratings. Our framework leverages pre-trained audio-text models such as CLAP and Audiobox-Aesthetics, and is trained exclusively on the official AudioMOS Challenge 2025 dataset. It demonstrates superior alignment with human evaluations across all dimensions, significantly outperforming robust baseline models.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08957
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems
Wang, Chien-Chun
Huang, Kuan-Tang
Yang, Cheng-Yeh
Lee, Hung-Shin
Wang, Hsin-Min
Chen, Berlin
Sound
Artificial Intelligence
Machine Learning
Evaluating audio generation systems, including text-to-music (TTM), text-to-speech (TTS), and text-to-audio (TTA), remains challenging due to the subjective and multi-dimensional nature of human perception. Existing methods treat mean opinion score (MOS) prediction as a regression problem, but standard regression losses overlook the relativity of perceptual judgments. To address this limitation, we introduce QAMRO, a novel Quality-aware Adaptive Margin Ranking Optimization framework that seamlessly integrates regression objectives from different perspectives, aiming to highlight perceptual differences and prioritize accurate ratings. Our framework leverages pre-trained audio-text models such as CLAP and Audiobox-Aesthetics, and is trained exclusively on the official AudioMOS Challenge 2025 dataset. It demonstrates superior alignment with human evaluations across all dimensions, significantly outperforming robust baseline models.
title QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems
topic Sound
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2508.08957