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 models in general, and Recurrent Neural Network Transducer (RNN-T)in particular, have gained significant traction in the automatic speechrecognition community in the last few years due to their simplicity,compactness, and excellent performance on generic transcription tasks. However,these models are more challenging to personalize compared to traditional hybridsystems due to the lack of external language models and difficulties inrecognizing rare long-tail words, specifically entity names. In this work, wepresent novel techniques to improve RNN-T's ability to model rare WordPieces,infuse extra information into the encoder, enable the use of alternativegraphemic pronunciations, and perform deep fusion with personalized languagemodels for more robust biasing. We show that these combined techniques resultin 15.4%-34.5% relative Word Error Rate improvement compared to a strong RNN-Tbaseline which uses shallow fusion and text-to-speech augmentation. Our workhelps push the boundary of RNN-T personalization and close the gap with hybridsystems on use cases where biasing and entity recognition are crucial.

Deep Shallow Fusion for RNN-T Personalization