用大模型结合音频事件推理，提升音频问答准确率。
Audio Question Answering with GRPO-Based Fine-Tuning and Calibrated Segment-Level Predictions
- 用BEATs提取音频特征，生成分段事件预测
- 通过校准提升事件级预测准确率至62.6%
- 适合做音频理解与大模型融合的研究者
本文描述了我们提交到DCASE 2025挑战赛第5赛道的音频问答（AQA）系统。系统基于自监督学习骨干BEATs提取帧级音频特征，并通过分类头生成符合Audioset本体的分段级事件预测。这些预测经校准后生成事件级结果，再与问题及候选答案构造成结构化提示，输入经GRPO算法微调的Qwen2.5-7B-Instruct模型。该方法在开发集上达到62.6%的准确率，证明了将声学事件推理与指令微调大语言模型结合在AQA任务中的有效性。
原文摘要 · Abstract (English)
In this report, we describe our submission to Track 5 of the DCASE 2025 Challenge for the task of Audio Question Answering(AQA). Our system leverages the SSL backbone BEATs to extract frame-level audio features, which are then processed by a classification head to generate segment-level predictions of acoustic events, following the Audioset ontology. These segment-level predictions are subsequently calibrated before producing event-level predictions. Finally, these predictions are incorporated into a structured prompt, along with the question and candidate answers. This prompt is then fed to a fine-tuned version of Qwen2.5-7B-Instruct, trained using the GRPO algorithm with a simple reward function. Our method achieves an accuracy of 62.6 % on the development set, demonstrating the effectiveness of combining acoustic event reasoning with instruction-tuned large language models for AQA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。