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

In this work, we explore the benefits of using multilingual bottleneckfeatures (mBNF) in acoustic modelling for the automatic speech recognition ofcode-switched (CS) speech in African languages. The unavailability of annotatedcorpora in the languages of interest has always been a primary challenge whendeveloping speech recognition systems for this severely under-resourced type ofspeech. Hence, it is worthwhile to investigate the potential of using speechcorpora available for other better-resourced languages to improve speechrecognition performance. To achieve this, we train a mBNF extractor using nineSouthern Bantu languages that form part of the freely available multilingualNCHLT corpus. We append these mBNFs to the existing MFCCs, pitch features andi-vectors to train acoustic models for automatic speech recognition (ASR) inthe target code-switched languages. Our results show that the inclusion of themBNF features leads to clear performance improvements over a baseline trainedwithout the mBNFs for code-switched English-isiZulu, English-isiXhosa,English-Sesotho and English-Setswana speech.

Multilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced Languages