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 (E2E) systems have shown comparable performance to hybrid systemsfor automatic speech recognition (ASR). Word timings, as a by-product of ASR,are essential in many applications, especially for subtitling andcomputer-aided pronunciation training. In this paper, we improve theframe-level classifier for word timings in E2E system by introducing labelpriors in connectionist temporal classification (CTC) loss, which is adoptedfrom prior works, and combining low-level Mel-scale filter banks withhigh-level ASR encoder output as input feature. On the internal Chinese corpus,the proposed method achieves 95.68%/94.18% compared to the hybrid system93.0%/90.22% on the word timing accuracy metrics. It also surpass a previousE2E approach with an absolute increase of 4.80%/8.02% on the metrics on 7languages. In addition, we further improve word timing accuracy by delaying CTCpeaks with frame-wise knowledge distillation, though only experimenting onLibriSpeech.

Improving Frame-level Classifier for Word Timings with Non-peaky CTC in End-to-End Automatic Speech Recognition