@inproceedings{nigmatulina-etal-2020-asr,
title = "{ASR} for Non-standardised Languages with Dialectal Variation: the case of {S}wiss {G}erman",
author = "Nigmatulina, Iuliia and
Kew, Tannon and
Samardzic, Tanja",
editor = {Zampieri, Marcos and
Nakov, Preslav and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Scherrer, Yves},
booktitle = "Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics (ICCL)",
url = "https://aclanthology.org/2020.vardial-1.2",
pages = "15--24",
abstract = "Strong regional variation, together with the lack of standard orthography, makes Swiss German automatic speech recognition (ASR) particularly difficult in a multi-dialectal setting. This paper focuses on one of the many challenges, namely, the choice of the output text to represent non-standardised Swiss German. We investigate two potential options: a) dialectal writing {--} approximate phonemic transcriptions that provide close correspondence between grapheme labels and the acoustic signal but are highly inconsistent and b) normalised writing {--} transcriptions resembling standard German that are relatively consistent but distant from the acoustic signal. To find out which writing facilitates Swiss German ASR, we build several systems using the Kaldi toolkit and a dataset covering 14 regional varieties. A formal comparison shows that the system trained on the normalised transcriptions achieves better results in word error rate (WER) (29.39{\%}) but underperforms at the character level, suggesting dialectal transcriptions offer a viable solution for downstream applications where dialectal differences are important. To better assess word-level performance for dialectal transcriptions, we use a flexible WER measure (FlexWER). When evaluated with this metric, the system trained on dialectal transcriptions outperforms that trained on the normalised writing. Besides establishing a benchmark for Swiss German multi-dialectal ASR, our findings can be helpful in designing ASR systems for other languages without standard orthography.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nigmatulina-etal-2020-asr">
<titleInfo>
<title>ASR for Non-standardised Languages with Dialectal Variation: the case of Swiss German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iuliia</namePart>
<namePart type="family">Nigmatulina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tannon</namePart>
<namePart type="family">Kew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Samardzic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics (ICCL)</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Strong regional variation, together with the lack of standard orthography, makes Swiss German automatic speech recognition (ASR) particularly difficult in a multi-dialectal setting. This paper focuses on one of the many challenges, namely, the choice of the output text to represent non-standardised Swiss German. We investigate two potential options: a) dialectal writing – approximate phonemic transcriptions that provide close correspondence between grapheme labels and the acoustic signal but are highly inconsistent and b) normalised writing – transcriptions resembling standard German that are relatively consistent but distant from the acoustic signal. To find out which writing facilitates Swiss German ASR, we build several systems using the Kaldi toolkit and a dataset covering 14 regional varieties. A formal comparison shows that the system trained on the normalised transcriptions achieves better results in word error rate (WER) (29.39%) but underperforms at the character level, suggesting dialectal transcriptions offer a viable solution for downstream applications where dialectal differences are important. To better assess word-level performance for dialectal transcriptions, we use a flexible WER measure (FlexWER). When evaluated with this metric, the system trained on dialectal transcriptions outperforms that trained on the normalised writing. Besides establishing a benchmark for Swiss German multi-dialectal ASR, our findings can be helpful in designing ASR systems for other languages without standard orthography.</abstract>
<identifier type="citekey">nigmatulina-etal-2020-asr</identifier>
<location>
<url>https://aclanthology.org/2020.vardial-1.2</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>15</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ASR for Non-standardised Languages with Dialectal Variation: the case of Swiss German
%A Nigmatulina, Iuliia
%A Kew, Tannon
%A Samardzic, Tanja
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Scherrer, Yves
%S Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2020
%8 December
%I International Committee on Computational Linguistics (ICCL)
%C Barcelona, Spain (Online)
%F nigmatulina-etal-2020-asr
%X Strong regional variation, together with the lack of standard orthography, makes Swiss German automatic speech recognition (ASR) particularly difficult in a multi-dialectal setting. This paper focuses on one of the many challenges, namely, the choice of the output text to represent non-standardised Swiss German. We investigate two potential options: a) dialectal writing – approximate phonemic transcriptions that provide close correspondence between grapheme labels and the acoustic signal but are highly inconsistent and b) normalised writing – transcriptions resembling standard German that are relatively consistent but distant from the acoustic signal. To find out which writing facilitates Swiss German ASR, we build several systems using the Kaldi toolkit and a dataset covering 14 regional varieties. A formal comparison shows that the system trained on the normalised transcriptions achieves better results in word error rate (WER) (29.39%) but underperforms at the character level, suggesting dialectal transcriptions offer a viable solution for downstream applications where dialectal differences are important. To better assess word-level performance for dialectal transcriptions, we use a flexible WER measure (FlexWER). When evaluated with this metric, the system trained on dialectal transcriptions outperforms that trained on the normalised writing. Besides establishing a benchmark for Swiss German multi-dialectal ASR, our findings can be helpful in designing ASR systems for other languages without standard orthography.
%U https://aclanthology.org/2020.vardial-1.2
%P 15-24
Markdown (Informal)
[ASR for Non-standardised Languages with Dialectal Variation: the case of Swiss German](https://aclanthology.org/2020.vardial-1.2) (Nigmatulina et al., VarDial 2020)
ACL