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

Automatic speech recognition (ASR) and speech translation (ST) can both useneural transducers as the model structure. It is thus possible to use a singletransducer model to perform both tasks. In real-world applications, such jointASR and ST models may need to be streaming and do not require source languageidentification (i.e. language-agnostic). In this paper, we propose LAMASSU, astreaming language-agnostic multilingual speech recognition and translationmodel using neural transducers. Based on the transducer model structure, wepropose four methods, a unified joint and prediction network for multilingualoutput, a clustered multilingual encoder, target language identification forencoder, and connectionist temporal classification regularization. Experimentalresults show that LAMASSU not only drastically reduces the model size but alsoreaches the performances of monolingual ASR and bilingual ST models.

LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers