Progressive Continual Learning for Spoken Keyword Spotting
This addresses the problem of updating deployed keyword spotting models without forgetting for applications like voice assistants, but it is incremental as it builds on existing continual learning methods.
The paper tackles catastrophic forgetting in keyword spotting models by proposing a progressive continual learning strategy, achieving 92.8% average accuracy after learning five new tasks on the Google Speech Command dataset.
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.