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

Building Spoken Language Understanding (SLU) robust to Automatic SpeechRecognition (ASR) errors is an essential issue for various voice-enabledvirtual assistants. Considering that most ASR errors are caused by phoneticconfusion between similar-sounding expressions, intuitively, leveraging thephoneme sequence of speech can complement ASR hypothesis and enhance therobustness of SLU. This paper proposes a novel model with Cross Attention forSLU (denoted as CASLU). The cross attention block is devised to catch thefine-grained interactions between phoneme and word embeddings in order to makethe joint representations catch the phonetic and semantic features of inputsimultaneously and for overcoming the ASR errors in downstream natural languageunderstanding (NLU) tasks. Extensive experiments are conducted on threedatasets, showing the effectiveness and competitiveness of our approach.Additionally, We also validate the universality of CASLU and prove itscomplementarity when combining with other robust SLU techniques.

Building Robust Spoken Language Understanding by Cross Attention between Phoneme Sequence and ASR Hypothesis