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 automatic speech recognition (ASR) models, including bothattention-based models and the recurrent neural network transducer (RNN-T),have shown superior performance compared to conventional systems. However,previous studies have focused primarily on short utterances that typically lastfor just a few seconds or, at most, a few tens of seconds. Whether sucharchitectures are practical on long utterances that last from minutes to hoursremains an open question. In this paper, we both investigate and improve theperformance of end-to-end models on long-form transcription. We first presentan empirical comparison of different end-to-end models on a real worldlong-form task and demonstrate that the RNN-T model is much more robust thanattention-based systems in this regime. We next explore two improvements toattention-based systems that significantly improve its performance: restrictingthe attention to be monotonic, and applying a novel decoding algorithm thatbreaks long utterances into shorter overlapping segments. Combining these twoimprovements, we show that attention-based end-to-end models can be verycompetitive to RNN-T on long-form speech recognition.

A comparison of end-to-end models for long-form speech recognition