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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Fine-tuning an Automatic Speech Recognition (ASR) model to new domainsresults in degradation on original domains, referred to as CatastrophicForgetting (CF). Continual Learning (CL) attempts to train ASR models withoutsuffering from CF. While in ASR, offline CL is usually considered, online CL isa more realistic but also more challenging scenario where the model, unlike inoffline CL, does not know when a task boundary occurs. Rehearsal-based methods,which store previously seen utterances in a memory, are often considered foronline CL, in ASR and other research domains. However, recent research hasshown that weight averaging is an effective method for offline CL in ASR. Basedon this result, we propose, in this paper, a rehearsal-free method applicablefor online CL. Our method outperforms all baselines, including rehearsal-basedmethods, in two experiments. Our method is a next step towards general CL forASR, which should enable CL in all scenarios with few if any constraints.

Rehearsal-Free Online Continual Learning for Automatic Speech Recognition