AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting

TL;DR

AnalyticKWS introduces an exemplar-free, efficient continual learning method for small-footprint keyword spotting that avoids data storage and reduces computational costs, effectively mitigating catastrophic forgetting in resource-limited environments.

Contribution

It proposes a novel analytical solution for incremental learning in keyword spotting, eliminating the need for data rehearsal and gradient-based updates.

Findings

Outperforms existing continual learning methods across multiple datasets.

Requires only a single epoch for model updates, enhancing efficiency.

Operates without storing old data, ensuring privacy and resource savings.

Abstract

Keyword spotting (KWS) offers a vital mechanism to identify spoken commands in voice-enabled systems, where user demands often shift, requiring models to learn new keywords continually over time. However, a major problem is catastrophic forgetting, where models lose their ability to recognize earlier keywords. Although several continual learning methods have proven their usefulness for reducing forgetting, most existing approaches depend on storing and revisiting old data to combat catastrophic forgetting. Though effective, these methods face two practical challenges: 1) privacy risks from keeping user data and 2) large memory and time consumption that limit deployment on small devices. To address these issues, we propose an exemplar-free Analytic Continual Learning (AnalyticKWS) method that updates model parameters without revisiting earlier data. Inspired by efficient learning principles, AnalyticKWS computes a closed-form analytical solution for model updates and requires only a single epoch of adaptation for incoming keywords. AnalyticKWS demands fewer computational resources by avoiding gradient-based updates and does not store old data. By eliminating the need for back-propagation during incremental learning, the model remains lightweight and efficient. As a result, AnalyticKWS meets the challenges mentioned earlier and suits resource-limited settings well. Extensive experiments on various datasets and settings show that AnalyticKWS consistently outperforms existing continual learning methods.