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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We propose a system to develop a basic automatic speech recognizer(ASR) forCantonese, a low-resource language, through transfer learning of Mandarin, ahigh-resource language. We take a time-delayed neural network trained onMandarin, and perform weight transfer of several layers to a newly initializedmodel for Cantonese. We experiment with the number of layers transferred, theirlearning rates, and pretraining i-vectors. Key findings are that this approachallows for quicker training time with less data. We find that for every epoch,log-probability is smaller for transfer learning models compared to aCantonese-only model. The transfer learning models show slight improvement inCER.

Cantonese Automatic Speech Recognition Using Transfer Learning from Mandarin