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/

Zendy Plus

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

Zendy Tools

Zendy Open

In this paper, we propose a novel spoken-text-style conversion method thatcan simultaneously execute multiple style conversion modules such aspunctuation restoration and disfluency deletion without preparing matcheddatasets. In practice, transcriptions generated by automatic speech recognitionsystems are not highly readable because they often include many disfluenciesand do not include punctuation marks. To improve their readability, multiplespoken-text-style conversion modules that individually model a singleconversion task are cascaded because matched datasets that simultaneouslyhandle multiple conversion tasks are often unavailable. However, the cascadingis unstable against the order of tasks because of the chain of conversionerrors. Besides, the computation cost of the cascading must be higher than thesingle conversion. To execute multiple conversion tasks simultaneously withoutpreparing matched datasets, our key idea is to distinguish individualconversion tasks using the on-off switch. In our proposed zero-shot jointmodeling, we switch the individual tasks using multiple switching tokens,enabling us to utilize a zero-shot learning approach to executing simultaneousconversions. Our experiments on joint modeling of disfluency deletion andpunctuation restoration demonstrate the effectiveness of our method.

Zero-Shot Joint Modeling of Multiple Spoken-Text-Style Conversion Tasks using Switching Tokens