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

We tackle the novel problem of navigational voice queries posed against anentertainment system, where viewers interact with a voice-enabled remotecontroller to specify the program to watch. This is a difficult problem forseveral reasons: such queries are short, even shorter than comparable voicequeries in other domains, which offers fewer opportunities for deciphering userintent. Furthermore, ambiguity is exacerbated by underlying speech recognitionerrors. We address these challenges by integrating word- and character-levelrepresentations of the queries and by modeling voice search sessions to capturethe contextual dependencies in query sequences. Both are accomplished with aprobabilistic framework in which recurrent and feedforward neural networkmodules are organized in a hierarchical manner. From a raw dataset of 32M voicequeries from 2.5M viewers on the Comcast Xfinity X1 entertainment system, weextracted data to train and test our models. We demonstrate the benefits of ourhybrid representation and context-aware model, which significantly outperformsmodels without context as well as the current deployed product.

Talking to Your TV: Context-Aware Voice Search with Hierarchical Recurrent Neural Networks