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/

Zendy Plus

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

Zendy Tools

Zendy Open

Accents play a pivotal role in shaping human communication, enhancing ourability to convey and comprehend messages with clarity and cultural nuance.While there has been significant progress in Automatic Speech Recognition(ASR), African-accented English ASR has been understudied due to a lack oftraining datasets, which are often expensive to create and demand colossalhuman labor. Combining several active learning paradigms and the core-setapproach, we propose a new multi-rounds adaptation process that uses epistemicuncertainty to automate the annotation process, significantly reducing theassociated costs and human labor. This novel method streamlines data annotationand strategically selects data samples contributing most to model uncertainty,enhancing training efficiency. We define a new U-WER metric to track modeladaptation to hard accents. We evaluate our approach across several domains,datasets, and high-performing speech models. Our results show that our approachleads to a 27\% WER relative average improvement while requiring on average45\% less data than established baselines. Our approach also improvesout-of-distribution generalization for very low-resource accents, demonstratingits viability for building generalizable ASR models in the context of accentedAfrican ASR. We open-source the code here:https://github.com/bonaventuredossou/active_learning_african_asr.

Advancing African-Accented Speech Recognition: Epistemic Uncertainty-Driven Data Selection for Generalizable ASR Models