@inproceedings{abulimiti-schultz-2020-automatic,
title = "Automatic Speech Recognition for {U}yghur through Multilingual Acoustic Modeling",
author = "Abulimiti, Ayimunishagu and
Schultz, Tanja",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.793",
pages = "6444--6449",
abstract = "Low-resource languages suffer from lower performance of Automatic Speech Recognition (ASR) system due to the lack of data. As a common approach, multilingual training has been applied to achieve more context coverage and has shown better performance over the monolingual training (Heigold et al., 2013). However, the difference between the donor language and the target language may distort the acoustic model trained with multilingual data, especially when much larger amount of data from donor languages is used for training the models of low-resource language. This paper presents our effort towards improving the performance of ASR system for the under-resourced Uyghur language with multilingual acoustic training. For the developing of multilingual speech recognition system for Uyghur, we used Turkish as donor language, which we selected from GlobalPhone corpus as the most similar language to Uyghur. By generating subsets of Uyghur training data, we explored the performance of multilingual speech recognition systems trained with different sizes of Uyghur and Turkish data. The best speech recognition system for Uyghur is achieved by multilingual training using all Uyghur data (10hours) and 17 hours of Turkish data and the WER is 19.17{\%}, which corresponds to 4.95{\%} relative improvement over monolingual training.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abulimiti-schultz-2020-automatic">
<titleInfo>
<title>Automatic Speech Recognition for Uyghur through Multilingual Acoustic Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayimunishagu</namePart>
<namePart type="family">Abulimiti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Schultz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Low-resource languages suffer from lower performance of Automatic Speech Recognition (ASR) system due to the lack of data. As a common approach, multilingual training has been applied to achieve more context coverage and has shown better performance over the monolingual training (Heigold et al., 2013). However, the difference between the donor language and the target language may distort the acoustic model trained with multilingual data, especially when much larger amount of data from donor languages is used for training the models of low-resource language. This paper presents our effort towards improving the performance of ASR system for the under-resourced Uyghur language with multilingual acoustic training. For the developing of multilingual speech recognition system for Uyghur, we used Turkish as donor language, which we selected from GlobalPhone corpus as the most similar language to Uyghur. By generating subsets of Uyghur training data, we explored the performance of multilingual speech recognition systems trained with different sizes of Uyghur and Turkish data. The best speech recognition system for Uyghur is achieved by multilingual training using all Uyghur data (10hours) and 17 hours of Turkish data and the WER is 19.17%, which corresponds to 4.95% relative improvement over monolingual training.</abstract>
<identifier type="citekey">abulimiti-schultz-2020-automatic</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.793</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6444</start>
<end>6449</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Speech Recognition for Uyghur through Multilingual Acoustic Modeling
%A Abulimiti, Ayimunishagu
%A Schultz, Tanja
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F abulimiti-schultz-2020-automatic
%X Low-resource languages suffer from lower performance of Automatic Speech Recognition (ASR) system due to the lack of data. As a common approach, multilingual training has been applied to achieve more context coverage and has shown better performance over the monolingual training (Heigold et al., 2013). However, the difference between the donor language and the target language may distort the acoustic model trained with multilingual data, especially when much larger amount of data from donor languages is used for training the models of low-resource language. This paper presents our effort towards improving the performance of ASR system for the under-resourced Uyghur language with multilingual acoustic training. For the developing of multilingual speech recognition system for Uyghur, we used Turkish as donor language, which we selected from GlobalPhone corpus as the most similar language to Uyghur. By generating subsets of Uyghur training data, we explored the performance of multilingual speech recognition systems trained with different sizes of Uyghur and Turkish data. The best speech recognition system for Uyghur is achieved by multilingual training using all Uyghur data (10hours) and 17 hours of Turkish data and the WER is 19.17%, which corresponds to 4.95% relative improvement over monolingual training.
%U https://aclanthology.org/2020.lrec-1.793
%P 6444-6449
Markdown (Informal)
[Automatic Speech Recognition for Uyghur through Multilingual Acoustic Modeling](https://aclanthology.org/2020.lrec-1.793) (Abulimiti & Schultz, LREC 2020)
ACL