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 translation is an essential communication task difficultfor humans whereby a translation is generated concurrently with oncoming speechinputs. For such a streaming task, transformers using block processing to breakan input sequence into segments have achieved state-of-the-art performance at areduced cost. Current methods to allow information to propagate acrosssegments, including left context and memory banks, have faltered as they areboth insufficient representations and unnecessarily expensive to compute. Inthis paper, we propose an Implicit Memory Transformer that implicitly retainsmemory through a new left context method, removing the need to explicitlyrepresent memory with memory banks. We generate the left context from theattention output of the previous segment and include it in the keys and valuesof the current segment's attention calculation. Experiments on the MuST-Cdataset show that the Implicit Memory Transformer provides a substantialspeedup on the encoder forward pass with nearly identical translation qualitywhen compared with the state-of-the-art approach that employs both left contextand memory banks.

Implicit Memory Transformer for Computationally Efficient Simultaneous Speech Translation