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

Wav2vec 2.0 is an end-to-end framework of self-supervised learning for speechrepresentation that is successful in automatic speech recognition (ASR), butmost of the work on the topic has been developed with a single language:English. Therefore, it is unclear whether the self-supervised framework iseffective in recognizing other languages with different writing systems, suchas Korean which uses the Hangul having a unique writing system. In this paper,we present K-Wav2Vec 2.0, which is a modified version of Wav2vec 2.0 designedfor Korean automatic speech recognition by exploring and optimizing variousfactors of the original Wav2vec 2.0. In fine-tuning, we propose a multi-taskhierarchical architecture to reflect the Korean writing structure. Moreover, ajoint decoder is applied to alleviate the problem of words existing outside ofthe vocabulary. In pre-training, we attempted the cross-lingual transfer of thepre-trained model by further pre-training the English Wav2vec 2.0 on a Koreandataset, considering limited resources. Our experimental results demonstratethat the proposed method yields the best performance on both Korean ASRdatasets: Ksponspeech (a large-scale Korean speech corpus) and Clovacall (acall-based dialog corpus). Further pre-training is also effective in languageadaptation, leading to large improvements without additional data.

K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables