Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models
Abstract
Recent advancements in multimodal reasoning have largely overlooked the audio modality. We introduce Audio-Reasoner, a large-scale audio language model for deep reasoning in audio tasks. We meticulously curated a large-scale and diverse multi-task audio dataset with simple annotations. Then, we leverage closed-source models to conduct secondary labeling, QA generation, along with structured COT process. These datasets together form a high-quality reasoning dataset with 1.2 million reasoning-rich samples, which we name CoTA. Following inference scaling principles, we train Audio-Reasoner on CoTA, enabling it to achieve great logical capabilities in audio reasoning. Experiments show state-of-the-art performance across key benchmarks, including MMAU-mini (+25.42%), AIR-Bench chat/foundation(+14.57%/+10.13%), and MELD (+8.01%). Our findings stress the core of structured CoT training in advancing audio reasoning.
Cite
@article{arxiv.2503.02318,
title = {Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models},
author = {Zhifei Xie and Mingbao Lin and Zihang Liu and Pengcheng Wu and Shuicheng Yan and Chunyan Miao},
journal= {arXiv preprint arXiv:2503.02318},
year = {2025}
}
Comments
Technical report, in process