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

Julia Pritzen, Michael Gref, Dietlind Zühlke, Christoph Andreas Schmidt

Abstract
Anglicisms are a challenge in German speech recognition. Due to their irregular pronunciation compared to native German words, automatically generated pronunciation dictionaries often contain incorrect phoneme sequences for Anglicisms. In this work, we propose a multitask sequence-to-sequence approach for grapheme-to-phoneme conversion to improve the phonetization of Anglicisms. We extended a grapheme-to-phoneme model with a classification task to distinguish Anglicisms from native German words. With this approach, the model learns to generate different pronunciations depending on the classification result. We used our model to create supplementary Anglicism pronunciation dictionaries to be added to an existing German speech recognition model. Tested on a special Anglicism evaluation set, we improved the recognition of Anglicisms compared to a baseline model, reducing the word error rate by a relative 1 % and the Anglicism error rate by a relative 3 %. With our experiment, we show that multitask learning can help solving the challenge of Anglicisms in German speech recognition.
Anthology ID:
2022.lrec-1.346
Volume:
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
3242–3249
Language:
URL:
https://aclanthology.org/2022.lrec-1.346
DOI:
Bibkey:
Cite (ACL):
Julia Pritzen, Michael Gref, Dietlind Zühlke, and Christoph Andreas Schmidt. 2022. Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in German Speech Recognition. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 3242–3249, Marseille, France. European Language Resources Association.
Cite (Informal):
Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in German Speech Recognition (Pritzen et al., LREC 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2022.lrec-1.346.pdf
PDF Search