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

Recently, recurrent neural network transducer (RNN-T) gains increasingpopularity due to its natural streaming capability as well as superiorperformance. Nevertheless, RNN-T training requires large time and computationresources as RNN-T loss calculation is slow and consumes a lot of memory.Another limitation of RNN-T is that it tends to access more contexts for betterperformance, thus leading to higher emission latency in streaming ASR. In thispaper we propose boundary-aware transducer (BAT) for memory-efficient andlow-latency ASR. In BAT, the lattice for RNN-T loss computation is reduced to arestricted region selected by the alignment from continuous integrate-and-fire(CIF), which is jointly optimized with the RNN-T model. Extensive experimentsdemonstrate that compared to RNN-T, BAT reduces time and memory consumptionsignificantly in training, and achieves good CER-latency trade-offs ininference for streaming ASR.

BAT: Boundary aware transducer for memory-efficient and low-latency ASR