Catastrophic forgetting is a thorny challenge when updating keyword spotting (KWS) models after deployment. This problem will be more challenging if KWS models are further required for edge devices due to their limited memory. To alleviate such an issue, we propose a novel diversity-aware incremental learning method named Rainbow Keywords (RK). Specifically, 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. 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. The scripts are available on GitHub.
翻译:在部署后更新关键字识别模型( KWS) 时, 灾难性的遗忘是一个棘手的挑战。 如果由于记忆有限, 边缘设备进一步需要 KWS 模型, 这个问题将更具挑战性。 为了缓解这一问题, 我们提议了一种新的多样性意识递增学习方法, 名为彩虹关键字( RK ) 。 具体地说, 拟议的 RK 方法引入了多样性意识取样器, 通过计算分类不确定性, 从历史和输入的关键字中选择多样化的数据集。 因此, RK 方法可以在不忘记先前知识的情况下逐步学习新任务。 此外, RK 方法还提议为边缘设备的有效记忆管理而增加数据和知识蒸馏损失功能。 实验结果显示, 拟议的RK 方法在比Google Speaction 数据集的最佳基线的平均精度方面实现了4. 2% 的绝对改进。 书稿可以在 GitHub 上查阅 。