English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Keyword Spotting (KWS) models are becoming increasingly integrated intovarious systems, e.g. voice assistants. To achieve satisfactory performance,these models typically rely on a large amount of labelled data, limiting theirapplications only to situations where such data is available. Self-supervisedLearning (SSL) methods can mitigate such a reliance by leveragingreadily-available unlabelled data. Most SSL methods for speech have primarilybeen studied for large models, whereas this is not ideal, as compact KWS modelsare generally required. This paper explores the effectiveness of SSL on smallmodels for KWS and establishes that SSL can enhance the performance of smallKWS models when labelled data is scarce. We pretrain three compacttransformer-based KWS models using Data2Vec, and fine-tune them on alabel-deficient setup of the Google Speech Commands data set. It is found thatData2Vec pretraining leads to a significant increase in accuracy, withlabel-deficient scenarios showing an improvement of 8.22% 11.18% absoluteaccuracy.

Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining