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

Recently, self-supervised pre-training has gained success in automatic speechrecognition (ASR). However, considering the difference between speech accentsin real scenarios, how to identify accents and use accent features to improveASR is still challenging. In this paper, we employ the self-supervisedpre-training method for both accent identification and accented speechrecognition tasks. For the former task, a standard deviation constraint loss(SDC-loss) based end-to-end (E2E) architecture is proposed to identify accentsunder the same language. As for accented speech recognition task, we design anaccent-dependent ASR system, which can utilize additional accent inputfeatures. Furthermore, we propose a frame-level accent feature, which isextracted based on the proposed accent identification model and can bedynamically adjusted. We pre-train our models using 960 hours unlabeledLibriSpeech dataset and fine-tune them on AESRC2020 speech dataset. Theexperimental results show that our proposed accent-dependent ASR system issignificantly ahead of the AESRC2020 baseline and achieves $6.5\%$ relativeword error rate (WER) reduction compared with our accent-independent ASRsystem.

Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-supervised Learning