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

Recent work on speech representation models jointly pre-trained with text hasdemonstrated the potential of improving speech representations by encodingspeech and text in a shared space. In this paper, we leverage such sharedrepresentations to address the persistent challenge of limited dataavailability in spoken language understanding tasks. By employing a pre-trainedspeech-text model, we find that models fine-tuned on text can be effectivelytransferred to speech testing data. With as little as 1 hour of labeled speechdata, our proposed approach achieves comparable performance on spoken languageunderstanding tasks (specifically, sentiment analysis and named entityrecognition) when compared to previous methods using speech-only pre-trainedmodels fine-tuned on 10 times more data. Beyond the proof-of-concept study, wealso analyze the latent representations. We find that the bottom layers ofspeech-text models are largely task-agnostic and align speech and textrepresentations into a shared space, while the top layers are moretask-specific.

Few-Shot Spoken Language Understanding via Joint Speech-Text Models