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

End-to-end (E2E) spoken language understanding (SLU) is constrained by thecost of collecting speech-semantics pairs, especially when label domainschange. Hence, we explore \textit{zero-shot} E2E SLU, which learns E2E SLUwithout speech-semantics pairs, instead using only speech-text andtext-semantics pairs. Previous work achieved zero-shot by pseudolabeling allspeech-text transcripts with a natural language understanding (NLU) modellearned on text-semantics corpora. However, this method requires the domains ofspeech-text and text-semantics to match, which often mismatch due to separatecollections. Furthermore, using the entire speech-text corpus from any domainsleads to \textit{imbalance} and \textit{noise} issues. To address these, wepropose \textit{cross-modal selective self-training} (CMSST). CMSST tacklesimbalance by clustering in a joint space of the three modalities (speech, text,and semantics) and handles label noise with a selection network. We alsointroduce two benchmarks for zero-shot E2E SLU, covering matched and foundspeech (mismatched) settings. Experiments show that CMSST improves performancein both two settings, with significantly reduced sample sizes and trainingtime.

Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training