Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning

2026-07-22

AI Summary

This work addresses the limitations of existing large audio language models, which struggle with fine-grained audio reasoning—such as understanding event order, repetition, and duration—and often rely on costly annotations or yield only coarse-grained semantics. To overcome these challenges, the authors propose Audio-Zero, the first self-evolving framework that operates without external labels. It constructs unsupervised contrastive audio pairs and introduces an auditory self-play mechanism: the model autonomously generates auditory cues and identifies “anomalous listeners” based on cue inconsistencies, driving reinforcement learning through verifiable intrinsic rewards. Evaluated on Qwen2-Audio-7B-Instruct and Qwen2.5-Omni-7B, this approach significantly improves performance on fine-grained reasoning benchmarks—including TREA, MMAU Test-mini, and MMAR—while preserving strong general audio understanding capabilities.

Abstract

Large Audio Language models (LALMs) have made rapid progress on acoustic understanding, yet they still struggle with fine-grained audio reasoning (e.g., recognizing event order, repetitions and duration). Existing post-training methods heavily rely on expensive external labels or provide only coarse semantic signals. To bridge this gap, we introduce Audio-Zero, the first label-free self-evolution framework in the field of LALMs that improves fine-grained auditory perception and reasoning. Audio-Zero constructs an auditory self-play game from unlabeled audio contrast pairs: most players hear a reference audio, while one odd listener hears a subtle variant. The model first generates clues describing what it hears and then identifies the odd listener by reasoning over inconsistencies among clues. Since the odd listener is known by construction, the game provides verifiable rewards without any annotated answers. Experiments with Qwen2-Audio-7B-Instruct and Qwen2.5-Omni-7B on TREA, MMAU Test-mini and MMAR show that Audio-Zero improves fine-grained audio reasoning while preserving broad audio understanding. Evolutionary and diagnostic analyses further reveal that increasingly fine-grained auditory descriptions emerge naturally from game pressure.

Problem

• fine-grained audio reasoning
• large audio language models
• label-free learning
• auditory perception
• self-evolution

Innovation

• label-free
• self-evolution
• fine-grained audio reasoning
• auditory self-play
• large audio language models