新声音事件可逐步学习，旧知识不丢失。
Class-Incremental Learning for Sound Event Localization and Detection
- 用误差最小化损失实现新类独立学习，保留旧类知识
- 在12类声音数据上，增量学习后各项指标保持稳定
- 适合需要持续新增声音类别的实际应用
本文研究了在声音事件定位与检测（SELD）任务中应用类别增量学习（CIL）的可行性。方法采用一个增量学习器，可在不遗忘旧类知识的前提下独立学习新声音类别。通过基于均方误差的蒸馏损失实现连续学习，以最小化后续学习器间的输出差异。实验在包含12种不同声音类别的TAU-NIGENS Spatial Sound Events 2021数据集上进行，初始学习8个类别，第二阶段引入4个新类别。增量学习完成后，在全部已学类别上评估系统性能。结果表明，对于这一真实场景数据集，所提方法在各项指标上均成功维持了基线性能。
原文摘要 · Abstract (English)
This paper investigates the feasibility of class-incremental learning (CIL) for Sound Event Localization and Detection (SELD) tasks. The method features an incremental learner that can learn new sound classes independently while preserving knowledge of old classes. The continual learning is achieved through a mean square error-based distillation loss to minimize output discrepancies between subsequent learners. The experiments are conducted on the TAU-NIGENS Spatial Sound Events 2021 dataset, which includes 12 different sound classes and demonstrate the efficacy of proposed method. We begin by learning 8 classes and introduce the 4 new classes at next stage. After the incremental phase, the system is evaluated on the full set of learned classes. Results show that, for this realistic dataset, our proposed method successfully maintains baseline performance across all metrics.
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。