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

The performance of automatic speech recognition (ASR) systems can besignificantly compromised by previously unseen conditions, which is typicallydue to a mismatch between training and testing distributions. In this paper, weaddress robustness by studying domain invariant features, such that domaininformation becomes transparent to ASR systems, resolving the mismatch problem.Specifically, we investigate a recent model, called the Factorized HierarchicalVariational Autoencoder (FHVAE). FHVAEs learn to factorize sequence-level andsegment-level attributes into different latent variables without supervision.We argue that the set of latent variables that contain segment-levelinformation is our desired domain invariant feature for ASR. Experiments areconducted on Aurora-4 and CHiME-4, which demonstrate 41% and 27% absolute worderror rate reductions respectively on mismatched domains.

Extracting Domain Invariant Features by Unsupervised Learning for Robust Automatic Speech Recognition