Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining
This addresses the reliance on large labeled datasets for compact keyword spotting models, which is incremental as it applies existing SSL methods to a specific domain.
The paper tackled the problem of keyword spotting with limited labeled data by using self-supervised pretraining on small models, resulting in an accuracy improvement of 8.22% to 11.18% in label-deficient scenarios.
Keyword Spotting (KWS) models are becoming increasingly integrated into various systems, e.g. voice assistants. To achieve satisfactory performance, these models typically rely on a large amount of labelled data, limiting their applications only to situations where such data is available. Self-supervised Learning (SSL) methods can mitigate such a reliance by leveraging readily-available unlabelled data. Most SSL methods for speech have primarily been studied for large models, whereas this is not ideal, as compact KWS models are generally required. This paper explores the effectiveness of SSL on small models for KWS and establishes that SSL can enhance the performance of small KWS models when labelled data is scarce. We pretrain three compact transformer-based KWS models using Data2Vec, and fine-tune them on a label-deficient setup of the Google Speech Commands data set. It is found that Data2Vec pretraining leads to a significant increase in accuracy, with label-deficient scenarios showing an improvement of 8.22% 11.18% absolute accuracy.