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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Anglicisms are a challenge in German speech recognition. Due to theirirregular pronunciation compared to native German words, automaticallygenerated pronunciation dictionaries often include faulty phoneme sequences forAnglicisms. In this work, we propose a multitask sequence-to-sequence approachfor grapheme-to-phoneme conversion to improve the phonetization of Anglicisms.We extended a grapheme-to-phoneme model with a classifier to distinguishAnglicisms from native German words. With this approach, the model learns togenerate pronunciations differently depending on the classification result. Weused our model to create supplementary Anglicism pronunciation dictionariesthat are added to an existing German speech recognition model. Tested on adedicated Anglicism evaluation set, we improved the recognition of Anglicismscompared to a baseline model, reducing the word error rate by 1 % and theAnglicism error rate by 3 %. We show that multitask learning can help solvingthe challenge of Anglicisms in German speech recognition.

Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in German Speech Recognition