QAMRO：用于音频生成系统人类对齐评估的质量感知自适应边际排序优化
QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems
AI总结：
针对音频生成系统评估中标准回归损失忽略感知相对性的问题，提出质量感知自适应边际排序优化框架QAMRO，整合多视角回归目标并利用预训练模型，在AudioMOS Challenge 2025数据集上实现了与人类评估更优的对齐。
摘要：
评估包括文本到音乐（TTM）、文本到语音（TTS）和文本到音频（TTA）在内的音频生成系统，由于人类感知的主观性和多维性，仍然具有挑战性。现有方法将平均意见分（MOS）预测视为回归问题，但标准回归损失忽略了感知判断的相对性。为了解决这一局限性，我们提出了QAMRO，一种新颖的质量感知自适应边际排序优化框架，该框架无缝整合了来自不同视角的回归目标，旨在突出感知差异并优先确保评分准确。我们的框架利用了CLAP和Audiobox-Aesthetics等预训练音频-文本模型，且仅在官方AudioMOS Challenge 2025数据集上进行训练。它在所有维度上均展现出与人类评估更优的对齐效果，显著优于鲁棒的基线模型。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
