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

Recently, end-to-end (E2E) automatic speech recognition (ASR) models havemade great strides and exhibit excellent performance in general speechrecognition. However, there remain several challenging scenarios that E2Emodels are not competent in, such as code-switching and named entityrecognition (NER). Data augmentation is a common and effective practice forthese two scenarios. However, the current data augmentation methods mainly relyon audio splicing and text-to-speech (TTS) models, which might result indiscontinuous, unrealistic, and less diversified speech. To mitigate thesepotential issues, we propose a novel data augmentation method by applying thetext-based speech editing model. The augmented speech from speech editingsystems is more coherent and diversified, also more akin to real speech. Theexperimental results on code-switching and NER tasks show that our proposedmethod can significantly outperform the audio splicing and neural TTS baseddata augmentation systems.

Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation