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

Accented speech recognition and accent classification are relativelyunder-explored research areas in speech technology. Recently, deeplearning-based methods and Transformer-based pretrained models have achievedsuperb performances in both areas. However, most accent classification tasksfocused on classifying different kinds of English accents and little attentionwas paid to geographically-proximate accent classification, especially under alow-resource setting where forensic speech science tasks usually encounter. Inthis paper, we explored three main accent modelling methods combined with twodifferent classifiers based on 105 speaker recordings retrieved from five urbanvarieties in Northern England. Although speech representations generated frompretrained models generally have better performances in downstreamclassification, traditional methods like Mel Frequency Cepstral Coefficients(MFCCs) and formant measurements are equipped with specific strengths. Theseresults suggest that in forensic phonetics scenario where data are relativelyscarce, a simple modelling method and classifier could be competitive withstate-of-the-art pretrained speech models as feature extractors, which couldenhance a sooner estimation for the accent information in practices. Besides,our findings also cross-validated a new methodology in quantifyingsociophonetic changes.

Low-resource Accent Classification in Geographically-proximate Settings: A Forensic and Sociophonetics Perspective