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

Most stuttering detection and classification research has viewed stutteringas a multi-class classification problem or a binary detection task for eachdysfluency type; however, this does not match the nature of stuttering, inwhich one dysfluency seldom comes alone but rather co-occurs with others. Thispaper explores multi-language and cross-corpus end-to-end stuttering detectionas a multi-label problem using a modified wav2vec 2.0 system with anattention-based classification head and multi-task learning. We evaluate themethod using combinations of three datasets containing English and Germanstuttered speech, one containing speech modified by fluency shaping. Theexperimental results and an error analysis show that multi-label stutteringdetection systems trained on cross-corpus and multi-language data achievecompetitive results but performance on samples with multiple labels stays belowover-all detection results.

A Stutter Seldom Comes Alone -- Cross-Corpus Stuttering Detection as a Multi-label Problem