paper-with-me

홈 › Papers

QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems

2025-08-12 · Chien-Chun Wang, Kuan-Tang Huang, Cheng-Yeh Yang, Hung-Shin Lee, Hsin-Min Wang, Berlin Chen arxiv

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.

📄 PDF Abstract BibTeX arXiv:2508.08957

Code (0)

등록된 구현이 없습니다.

Tasks

Audio Generation

Similar Papers 제목 키워드 기반

MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling

2026-02-19 · Payel Bhattacharjee, Osvaldo Simeone, Ravi Tandon arxiv

Reward modeling is central to alignment pipelines such as RLHF, RLAIF, and PPO-based policy optimization, yet its reliability is constrained by limited and heterogeneous human preference data that are expensive to collec…

Data Augmentation

MR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment

2026-06-29 · Yuan Li, Youyuan Lin, Zitang Sun, Yung-Hao Yang 외 arxiv

Blind image quality assessment (BIQA) is commonly built on two basic learning paradigms: regression and ranking. Regression calibrates absolute scores, whereas ranking recovers quality structure from ordinal relations. A…

Image Quality AssessmentReinforcement Learning

SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detection

2024-03-12 · Hongcheng Zhang, Liu Liang, Pengxin Zeng, Xiao Song 외

Sparse 3D detectors have received significant attention since the query-based paradigm embraces low latency without explicit dense BEV feature construction. However, these detectors achieve worse performance than their d…

3D Object Detectionobject-detectionObject Detection

ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval

2024-03-11 · Yuanhang Zheng, Peng Li, Wei Liu, Yang Liu 외

Tool learning aims to extend the capabilities of large language models (LLMs) with external tools. A major challenge in tool learning is how to support a large number of tools, including unseen tools. To address this cha…

RerankingRetrieval

Optimizing Preference Alignment with Differentiable NDCG Ranking

2024-10-17 · Jiacong Zhou, Xianyun Wang, Jun Yu

Aligning large language models with human preferences improves interaction quality and safety by ensuring outputs better reflect human values. A promising strategy involves Reinforcement Learning from Human Feedback (RLH…

Learning-To-Rank