<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vesik-etal-2020-one">
    <titleInfo>
        <title>One Model to Pronounce Them All: Multilingual Grapheme-to-Phoneme Conversion With a Transformer Ensemble</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kaili</namePart>
        <namePart type="family">Vesik</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Muhammad</namePart>
        <namePart type="family">Abdul-Mageed</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Miikka</namePart>
        <namePart type="family">Silfverberg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Garrett</namePart>
            <namePart type="family">Nicolai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kyle</namePart>
            <namePart type="family">Gorman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ryan</namePart>
            <namePart type="family">Cotterell</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The task of grapheme-to-phoneme (G2P) conversion is important for both speech recognition and synthesis. Similar to other speech and language processing tasks, in a scenario where only small-sized training data are available, learning G2P models is challenging. We describe a simple approach of exploiting model ensembles, based on multilingual Transformers and self-training, to develop a highly effective G2P solution for 15 languages. Our models are developed as part of our participation in the SIGMORPHON 2020 Shared Task 1 focused at G2P. Our best models achieve 14.99 word error rate (WER) and 3.30 phoneme error rate (PER), a sizeable improvement over the shared task competitive baselines.</abstract>
    <identifier type="citekey">vesik-etal-2020-one</identifier>
    <identifier type="doi">10.18653/v1/2020.sigmorphon-1.16</identifier>
    <location>
        <url>https://aclanthology.org/2020.sigmorphon-1.16</url>
    </location>
    <part>
        <date>2020-07</date>
        <extent unit="page">
            <start>146</start>
            <end>152</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T One Model to Pronounce Them All: Multilingual Grapheme-to-Phoneme Conversion With a Transformer Ensemble
%A Vesik, Kaili
%A Abdul-Mageed, Muhammad
%A Silfverberg, Miikka
%Y Nicolai, Garrett
%Y Gorman, Kyle
%Y Cotterell, Ryan
%S Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F vesik-etal-2020-one
%X The task of grapheme-to-phoneme (G2P) conversion is important for both speech recognition and synthesis. Similar to other speech and language processing tasks, in a scenario where only small-sized training data are available, learning G2P models is challenging. We describe a simple approach of exploiting model ensembles, based on multilingual Transformers and self-training, to develop a highly effective G2P solution for 15 languages. Our models are developed as part of our participation in the SIGMORPHON 2020 Shared Task 1 focused at G2P. Our best models achieve 14.99 word error rate (WER) and 3.30 phoneme error rate (PER), a sizeable improvement over the shared task competitive baselines.
%R 10.18653/v1/2020.sigmorphon-1.16
%U https://aclanthology.org/2020.sigmorphon-1.16
%U https://doi.org/10.18653/v1/2020.sigmorphon-1.16
%P 146-152

Markdown (Informal)

[One Model to Pronounce Them All: Multilingual Grapheme-to-Phoneme Conversion With a Transformer Ensemble](https://aclanthology.org/2020.sigmorphon-1.16) (Vesik et al., SIGMORPHON 2020)

• One Model to Pronounce Them All: Multilingual Grapheme-to-Phoneme Conversion With a Transformer Ensemble (Vesik et al., SIGMORPHON 2020)

ACL

• Kaili Vesik, Muhammad Abdul-Mageed, and Miikka Silfverberg. 2020. One Model to Pronounce Them All: Multilingual Grapheme-to-Phoneme Conversion With a Transformer Ensemble. In Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 146–152, Online. Association for Computational Linguistics.