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

Domain mismatch between training and testing can lead to significantdegradation in performance in many machine learning scenarios. Unfortunately,this is not a rare situation for automatic speech recognition deployments inreal-world applications. Research on robust speech recognition can be regardedas trying to overcome this domain mismatch issue. In this paper, we address theunsupervised domain adaptation problem for robust speech recognition, whereboth source and target domain speech are presented, but word transcripts areonly available for the source domain speech. We present novelaugmentation-based methods that transform speech in a way that does not changethe transcripts. Specifically, we first train a variational autoencoder on bothsource and target domain data (without supervision) to learn a latentrepresentation of speech. We then transform nuisance attributes of speech thatare irrelevant to recognition by modifying the latent representations, in orderto augment labeled training data with additional data whose distribution ismore similar to the target domain. The proposed method is evaluated on theCHiME-4 dataset and reduces the absolute word error rate (WER) by as much as35% compared to the non-adapted baseline.

Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation