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

Training state-of-the-art Automated Speech Recognition (ASR) models typicallyrequires a substantial amount of transcribed speech. In this work, wedemonstrate that a modality-matched joint speech and text model can beleveraged to train a massively multilingual ASR model without any supervised(manually transcribed) speech for some languages. This paper explores the useof jointly learnt speech and text representations in a massively multilingual,zero supervised speech, real-world setting to expand the set of languagescovered by ASR with only unlabeled speech and text in the target languages.Using the FLEURS dataset, we define the task to cover $102$ languages, wheretranscribed speech is available in $52$ of these languages and can be used toimprove end-to-end ASR quality on the remaining $50$. First, we show that bycombining speech representations with byte-level text representations and useof language embeddings, we can dramatically reduce the Character Error Rate(CER) on languages with no supervised speech from 64.8\% to 30.8\%, a relativereduction of 53\%. Second, using a subset of South Asian languages we show thatMaestro-U can promote knowledge transfer from languages with supervised speecheven when there is limited to no graphemic overlap. Overall, Maestro-U closesthe gap to oracle performance by 68.5\% relative and reduces the CER of 19languages below 15\%.

Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASR