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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Speech-enabled systems typically first convert audio to text through anautomatic speech recognition (ASR) model and then feed the text to downstreamnatural language processing (NLP) modules. The errors of the ASR system canseriously downgrade the performance of the NLP modules. Therefore, it isessential to make them robust to the ASR errors. Previous work has shown it iseffective to employ data augmentation methods to solve this problem byinjecting ASR noise during the training process. In this paper, we utilize theprevalent pre-trained language model to generate training samples withASR-plausible noise. Compare to the previous methods, our approach generatesASR noise that better fits the real-world error distribution. Experimentalresults on spoken language translation(SLT) and spoken language understanding(SLU) show that our approach effectively improves the system robustness againstthe ASR errors and achieves state-of-the-art results on both tasks.

An Approach to Improve Robustness of NLP Systems against ASR Errors