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

Online speech recognition, where the model only accesses context to the left,is an important and challenging use case for ASR systems. In this work, weinvestigate augmenting neural encoders for online ASR by incorporatingstructured state-space sequence models (S4), a family of models that provide aparameter-efficient way of accessing arbitrarily long left context. Weperformed systematic ablation studies to compare variants of S4 models andpropose two novel approaches that combine them with convolutions. We found thatthe most effective design is to stack a small S4 using real-valued recurrentweights with a local convolution, allowing them to work complementarily. Ourbest model achieves WERs of 4.01%/8.53% on test sets from Librispeech,outperforming Conformers with extensively tuned convolution.

Augmenting conformers with structured state-space sequence models for online speech recognition