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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The lack of code-switch training data is one of the major concerns in thedevelopment of end-to-end code-switching automatic speech recognition (ASR)models. In this work, we propose a method to train an improved end-to-endcode-switching ASR using only monolingual data. Our method encourages thedistributions of output token embeddings of monolingual languages to besimilar, and hence, promotes the ASR model to easily code-switch betweenlanguages. Specifically, we propose to use Jensen-Shannon divergence and cosinedistance based constraints. The former will enforce output embeddings ofmonolingual languages to possess similar distributions, while the later simplybrings the centroids of two distributions to be close to each other.Experimental results demonstrate high effectiveness of the proposed method,yielding up to 4.5% absolute mixed error rate improvement on Mandarin-Englishcode-switching ASR task.

Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data