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 Spoken Language Understanding (E2E SLU) has attracted increasinginterest due to its advantages of joint optimization and low latency whencompared to traditionally cascaded pipelines. Existing E2E SLU models usuallyfollow a two-stage configuration where an Automatic Speech Recognition (ASR)network first predicts a transcript which is then passed to a Natural LanguageUnderstanding (NLU) module through an interface to infer semantic labels, suchas intent and slot tags. This design, however, does not consider the NLUposterior while making transcript predictions, nor correct the NLU predictionerror immediately by considering the previously predicted word-pieces. Inaddition, the NLU model in the two-stage system is not streamable, as it mustwait for the audio segments to complete processing, which ultimately impactsthe latency of the SLU system. In this work, we propose a streamable multi-tasksemantic transducer model to address these considerations. Our proposedarchitecture predicts ASR and NLU labels auto-regressively and uses a semanticdecoder to ingest both previously predicted word-pieces and slot tags whileaggregating them through a fusion network. Using an industry scale SLU and apublic FSC dataset, we show the proposed model outperforms the two-stage E2ESLU model for both ASR and NLU metrics.

Multi-task RNN-T with Semantic Decoder for Streamable Spoken Language Understanding