@inproceedings{yadav-sitaram-2022-survey,
title = "A Survey of Multilingual Models for Automatic Speech Recognition",
author = "Yadav, Hemant and
Sitaram, Sunayana",
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-1.542",
pages = "5071--5079",
abstract = "Although Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, the majority of the world{'}s languages do not have usable systems due to the lack of large speech datasets to train these models. Cross-lingual transfer is an attractive solution to this problem, because low-resource languages can potentially benefit from higher-resource languages either through transfer learning, or being jointly trained in the same multilingual model. The problem of cross-lingual transfer has been well studied in ASR, however, recent advances in Self Supervised Learning are opening up avenues for unlabeled speech data to be used in multilingual ASR models, which can pave the way for improved performance on low-resource languages. In this paper, we survey the state of the art in multilingual ASR models that are built with cross-lingual transfer in mind. We present best practices for building multilingual models from research across diverse languages and techniques, discuss open questions and provide recommendations for future work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yadav-sitaram-2022-survey">
<titleInfo>
<title>A Survey of Multilingual Models for Automatic Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hemant</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</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>Although Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, the majority of the world’s languages do not have usable systems due to the lack of large speech datasets to train these models. Cross-lingual transfer is an attractive solution to this problem, because low-resource languages can potentially benefit from higher-resource languages either through transfer learning, or being jointly trained in the same multilingual model. The problem of cross-lingual transfer has been well studied in ASR, however, recent advances in Self Supervised Learning are opening up avenues for unlabeled speech data to be used in multilingual ASR models, which can pave the way for improved performance on low-resource languages. In this paper, we survey the state of the art in multilingual ASR models that are built with cross-lingual transfer in mind. We present best practices for building multilingual models from research across diverse languages and techniques, discuss open questions and provide recommendations for future work.</abstract>
<identifier type="citekey">yadav-sitaram-2022-survey</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.542</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5071</start>
<end>5079</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Survey of Multilingual Models for Automatic Speech Recognition
%A Yadav, Hemant
%A Sitaram, Sunayana
%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 yadav-sitaram-2022-survey
%X Although Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, the majority of the world’s languages do not have usable systems due to the lack of large speech datasets to train these models. Cross-lingual transfer is an attractive solution to this problem, because low-resource languages can potentially benefit from higher-resource languages either through transfer learning, or being jointly trained in the same multilingual model. The problem of cross-lingual transfer has been well studied in ASR, however, recent advances in Self Supervised Learning are opening up avenues for unlabeled speech data to be used in multilingual ASR models, which can pave the way for improved performance on low-resource languages. In this paper, we survey the state of the art in multilingual ASR models that are built with cross-lingual transfer in mind. We present best practices for building multilingual models from research across diverse languages and techniques, discuss open questions and provide recommendations for future work.
%U https://aclanthology.org/2022.lrec-1.542
%P 5071-5079
Markdown (Informal)
[A Survey of Multilingual Models for Automatic Speech Recognition](https://aclanthology.org/2022.lrec-1.542) (Yadav & Sitaram, LREC 2022)
ACL