论文标题
渐进式持续学习关键字发现
Progressive Continual Learning for Spoken Keyword Spotting
论文作者
论文摘要
部署后更新关键字发现（KWS）模型时，灾难性遗忘是一个棘手的挑战。为了应对此类挑战，我们提出了针对小英寸小英寸口语关键字点（PCL-KWS）的渐进式持续学习策略。具体而言，提出的PCL-KWS框架引入了网络实例化器，以生成特定任务的子网络，用于记住以前学习的关键字。结果，PCL-KWS方法会逐步学习新的关键字，而无需忘记先验知识。此外，PCL-KWS的关键字感知网络缩放机制在实现高性能的同时限制了模型参数的增长。实验结果表明，在依次学习了五项新任务之后，我们提出的PCL-KWS方法归档了与其他基线相比，Google语音命令数据集上所有任务的新最新性能为92.8％的平均准确性。
Catastrophic forgetting is a thorny challenge when updating keyword spotting (KWS) models after deployment. To tackle such challenges, we propose a progressive continual learning strategy for small-footprint spoken keyword spotting (PCL-KWS). Specifically, the proposed PCL-KWS framework introduces a network instantiator to generate the task-specific sub-networks for remembering previously learned keywords. As a result, the PCL-KWS approach incrementally learns new keywords without forgetting prior knowledge. Besides, the keyword-aware network scaling mechanism of PCL-KWS constrains the growth of model parameters while achieving high performance. Experimental results show that after learning five new tasks sequentially, our proposed PCL-KWS approach archives the new state-of-the-art performance of 92.8% average accuracy for all the tasks on Google Speech Command dataset compared with other baselines.
