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

For many of the 700 million illiterate people around the world, speechrecognition technology could provide a bridge to valuable information andservices. Yet, those most in need of this technology are often the mostunderserved by it. In many countries, illiterate people tend to speak onlylow-resource languages, for which the datasets necessary for speech technologydevelopment are scarce. In this paper, we investigate the effectiveness ofunsupervised speech representation learning on noisy radio broadcastingarchives, which are abundant even in low-resource languages. We make three corecontributions. First, we release two datasets to the research community. Thefirst, West African Radio Corpus, contains 142 hours of audio in more than 10languages with a labeled validation subset. The second, West African VirtualAssistant Speech Recognition Corpus, consists of 10K labeled audio clips infour languages. Next, we share West African wav2vec, a speech encoder trainedon the noisy radio corpus, and compare it with the baseline Facebook speechencoder trained on six times more data of higher quality. We show that WestAfrican wav2vec performs similarly to the baseline on a multilingual speechrecognition task, and significantly outperforms the baseline on a West Africanlanguage identification task. Finally, we share the first-ever speechrecognition models for Maninka, Pular and Susu, languages spoken by a combined10 million people in over seven countries, including six where the majority ofthe adult population is illiterate. Our contributions offer a path forward forethical AI research to serve the needs of those most disadvantaged by thedigital divide.

Using Radio Archives for Low-Resource Speech Recognition: Towards an Intelligent Virtual Assistant for Illiterate Users