提出新方法实现设备端音频事件分类持续学习，不遗忘旧知识。
Continual Learning for Acoustic Event Classification
- 用分类不确定性挑选历史数据，提升增量学习多样性。
- 在语音命令数据集上平均准确率提升4.2%，内存需求更低。
- 适合资源受限的边缘设备，支持高效持续学习新音频类别。
在计算资源受限（如模型大小、运行内存）的设备端音频事件分类中，持续学习新类别而避免灾难性遗忘是一个挑战。为此，我们提出了两种新颖的多样性感知增量学习方法，应用于语音关键词检测和环境声音分类。针对语音关键词检测，所提RK方法通过计算分类不确定性，从历史与新到来的关键词中选择多样化的样本进行训练，从而实现无遗忘的增量学习。此外，该方法引入数据增强和知识蒸馏损失函数，以高效管理边缘设备上的内存。对于环境声音分类，通过观察分类概率在分类器嵌入添加并行扰动下的波动来衡量不确定性，相比对原始数据加扰动显著降低计算开销。实验表明，该方法在Google Speech Commands数据集上相比最优基线平均准确率提升4.2%，所需内存更少；在DCASE 2019 Task 1和ESC-50数据集上，分类准确率和计算效率均优于基线持续学习方法，证明其可有效实现无遗忘的增量学习。
原文摘要 · Abstract (English)
Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device acoustic event classification given the restrictions on computation resources (e.g., model size, running memory). To alleviate such an issue, we propose two novel diversity-aware incremental learning method for Spoken Keyword Spotting and Environmental Sound Classification. Our method selects the historical data for the training by measuring the per-sample classification uncertainty. For the Spoken Keyword Spotting application, the proposed RK approach introduces a diversity-aware sampler to select a diverse set from historical and incoming keywords by calculating classification uncertainty. As a result, the RK approach can incrementally learn new tasks without forgetting prior knowledge. Besides, the RK approach also proposes data augmentation and knowledge distillation loss function for efficient memory management on the edge device. For the Environmental Sound Classification application, we measure the uncertainty by observing how the classification probability of data fluctuates against the parallel perturbations added to the classifier embedding. In this way, the computation cost can be significantly reduced compared with adding perturbation to the raw data. Experimental results show that the proposed RK approach achieves 4.2% absolute improvement in terms of average accuracy over the best baseline on Google Speech Command dataset with less required memory. Experimental results on the DCASE 2019 Task 1 and ESC-50 dataset show that our proposed method outperforms baseline continual learning methods on classification accuracy and computational efficiency, indicating our method can efficiently and incrementally learn new classes without the catastrophic forgetting problem for on-device environmental sound classification
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。