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

Recently, speech-text pre-training methods have shown remarkable success inmany speech and natural language processing tasks. However, most previouspre-trained models are usually tailored for one or two specific tasks, but failto conquer a wide range of speech-text tasks. In addition, existing speech-textpre-training methods fail to explore the contextual information within adialogue to enrich utterance representations. In this paper, we proposeSpeech-text dialog Pre-training for spoken dialog understanding with ExpliCiTcRoss-Modal Alignment (SPECTRA), which is the first-ever speech-text dialogpre-training model. Concretely, to consider the temporality of speech modality,we design a novel temporal position prediction task to capture the speech-textalignment. This pre-training task aims to predict the start and end time ofeach textual word in the corresponding speech waveform. In addition, to learnthe characteristics of spoken dialogs, we generalize a response selection taskfrom textual dialog pre-training to speech-text dialog pre-training scenarios.Experimental results on four different downstream speech-text tasks demonstratethe superiority of SPECTRA in learning speech-text alignment and multi-turndialog context.

Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment