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

Simultaneous speech-to-text translation is widely useful in many scenarios.The conventional cascaded approach uses a pipeline of streaming ASR followed bysimultaneous MT, but suffers from error propagation and extra latency. Toalleviate these issues, recent efforts attempt to directly translate the sourcespeech into target text simultaneously, but this is much harder due to thecombination of two separate tasks. We instead propose a new paradigm with theadvantages of both cascaded and end-to-end approaches. The key idea is to usetwo separate, but synchronized, decoders on streaming ASR and directspeech-to-text translation (ST), respectively, and the intermediate results ofASR guide the decoding policy of (but is not fed as input to) ST. Duringtraining time, we use multitask learning to jointly learn these two tasks witha shared encoder. En-to-De and En-to-Es experiments on the MuSTC datasetdemonstrate that our proposed technique achieves substantially bettertranslation quality at similar levels of latency.

Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR