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 rise of bidirectional encoder representations from Transformermodels in natural language processing, the speech community has adopted some oftheir development methodologies. Therefore, the Wav2Vec models were introducedto reduce the data required to obtain state-of-the-art results. This workleverages this knowledge and improves the performance of the pre-trained speechmodels by simply replacing the fine-tuning dense layer with a lateralinhibition layer inspired by the biological process. Our experiments onRomanian, a low-resource language, show an average improvement of 12.5% worderror rate (WER) using the lateral inhibition layer. In addition, we obtainstate-of-the-art results on both the Romanian Speech Corpus and the RobinTechnical Acquisition Corpus with 1.78% WER and 29.64% WER, respectively.

Towards Improving the Performance of Pre-Trained Speech Models for Low-Resource Languages Through Lateral Inhibition