QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Audio GenerationSimilar Papers 제목 키워드 기반
MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling
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 AugmentationMR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment
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 LearningSparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detection
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 DetectionToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval
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…
RerankingRetrievalOptimizing Preference Alignment with Differentiable NDCG Ranking
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