Abstract
In this technical report, we describe our submission for Task 1, Low-Complexity Device-Robust Acoustic Scene Classification, of the DCASE 2025 Challenge. Our work tackles the dual challenges of strict complexity constraints and robust generalization to both seen and unseen devices, while also leveraging the new rule allowing the use of device labels at test time. Our proposed system is based on a knowledge distillation framework where an efficient CP-MobileNet student learns from a compact, specialized two-teacher ensemble. This ensemble combines a baseline PaSST teacher, trained with standard cross-entropy, and a 'generalization expert' teacher. This expert is trained using our novel Device-Aware Feature Alignment (DAFA) loss, adapted from prior work, which explicitly structures the feature space for device robustness. To capitalize on the availability of test-time device labels, the distilled student model then undergoes a final device-specific fine-tuning stage. Our proposed system achieves a final accuracy of 57.93\% on the development set, demonstrating a significant improvement over the official baseline, particularly on unseen devices.
Abstract (translated)
在这份技术报告中，我们描述了针对DCASE 2025挑战赛任务1——低复杂度设备鲁棒声学场景分类的参赛方案。我们的工作旨在应对严格的复杂性限制和对已见及未见过设备的强大泛化能力这双重挑战，并且还利用了新规则允许在测试时使用设备标签的规定。我们提出的系统基于知识蒸馏框架，其中高效的CP-MobileNet学生模型从一个紧凑的专业双教师集合中学习。这个集合结合了一个基线PaSST教师（通过标准交叉熵训练）和一个“泛化专家”教师。该专家是通过我们的新方法Device-Aware Feature Alignment (DAFA) 损失进行训练的，该损失借鉴了先前的工作，并明确地构建了设备鲁棒性的特征空间结构。为了利用测试时可用的设备标签信息，蒸馏后的学生模型随后会经历一个特定于设备的最终微调阶段。我们的系统在开发集上达到了57.93%的最终准确率，相较于官方基准线，特别是在未见过的设备上取得了显著的进步。
URL
https://arxiv.org/abs/2509.09262
