@inproceedings{pritzen-etal-2022-multitask,
title = "Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in {G}erman Speech Recognition",
author = {Pritzen, Julia and
Gref, Michael and
Z{\"u}hlke, Dietlind and
Schmidt, Christoph Andreas},
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.346",
pages = "3242--3249",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pritzen-etal-2022-multitask">
<titleInfo>
<title>Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in German Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Pritzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Gref</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietlind</namePart>
<namePart type="family">Zühlke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="given">Andreas</namePart>
<namePart type="family">Schmidt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">pritzen-etal-2022-multitask</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.346</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3242</start>
<end>3249</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in German Speech Recognition
%A Pritzen, Julia
%A Gref, Michael
%A Zühlke, Dietlind
%A Schmidt, Christoph Andreas
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F pritzen-etal-2022-multitask
%X 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.
%U https://aclanthology.org/2022.lrec-1.346
%P 3242-3249
Markdown (Informal)
[Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in German Speech Recognition](https://aclanthology.org/2022.lrec-1.346) (Pritzen et al., LREC 2022)
ACL