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

Arabic dialect identification (ADI) tools are an important part of thelarge-scale data collection pipelines necessary for training speech recognitionmodels. As these pipelines require application of ADI tools to potentiallyout-of-domain data, we aim to investigate how vulnerable the tools may be tothis domain shift. With self-supervised learning (SSL) models as a startingpoint, we evaluate transfer learning and direct classification from SSLfeatures. We undertake our evaluation under rich conditions, with a goal todevelop ADI systems from pretrained models and ultimately evaluate performanceon newly collected data. In order to understand what factors contribute tomodel decisions, we carry out a careful human study of a subset of our data.Our analysis confirms that domain shift is a major challenge for ADI models. Wealso find that while self-training does alleviate this challenges, it may beinsufficient for realistic conditions.

On the Robustness of Arabic Speech Dialect Identification