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

With the acceleration of globalization, more and more people are willing orrequired to learn second languages (L2). One of the major remaining challengesfacing current mispronunciation and diagnosis (MDD) models for use incomputer-assisted pronunciation training (CAPT) is to handle speech from L2learners with a diverse set of accents. In this paper, we set out to mitigatethe adverse effects of accent variety in building an L2 English MDD system withend-to-end (E2E) neural models. To this end, we first propose an effectivemodeling framework that infuses accent features into an E2E MDD model, therebymaking the model more accent-aware. Going a step further, we design and presentdisparate accent-aware modules to perform accent-aware modulation of acousticfeatures in a finer-grained manner, so as to enhance the discriminatingcapability of the resulting MDD model. Extensive sets of experiments conductedon the L2-ARCTIC benchmark dataset show the merits of our MDD model, incomparison to some existing E2E-based strong baselines and the celebratedpronunciation scoring based method.

Towards Robust Mispronunciation Detection and Diagnosis for L2 English Learners with Accent-Modulating Methods