Internet Archive Scholar
Filters
























1 Hit in 4.9 sec

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

Julia Pritzen, Michael Gref, Dietlind Zühlke, Christoph Schmidt
2021 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (194.5 kB)
https://web.archive.org/web/20210708074343/https://arxiv.org/pdf/2105.12708v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

Other Versions

2021 pre-print
arXiv:2105.12708v1 fatcat:xnybtoupxrg2bcqkxxyr56tvsq
In this work, we propose a multitask sequence-to-sequence approach for grapheme-to-phoneme conversion to improve the phonetization of Anglicisms.  ...  We show that multitask learning can help solving the challenge of loanwords in German speech recognition.  ...  To solve this problem, we used multitask learning (MTL) to detect Anglicisms in a second classification task parallel to G2P conversion.  ... 
arXiv:2105.12708v2 fatcat:fcs3xn3v2zbzxkgwd6qjrtaetq
Multiple Versions
Citation

Julia Pritzen, Michael Gref, Dietlind Zühlke, Christoph Schmidt. "Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in German Speech Recognition." arXiv (2021)