@inproceedings{shi-etal-2021-highland,
title = "{H}ighland {P}uebla {N}ahuatl Speech Translation Corpus for Endangered Language Documentation",
author = "Shi, Jiatong and
Amith, Jonathan D. and
Chang, Xuankai and
Dalmia, Siddharth and
Yan, Brian and
Watanabe, Shinji",
editor = "Mager, Manuel and
Oncevay, Arturo and
Rios, Annette and
Ruiz, Ivan Vladimir Meza and
Palmer, Alexis and
Neubig, Graham and
Kann, Katharina",
booktitle = "Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.americasnlp-1.7",
doi = "10.18653/v1/2021.americasnlp-1.7",
pages = "53--63",
abstract = "Documentation of endangered languages (ELs) has become increasingly urgent as thousands of languages are on the verge of disappearing by the end of the 21st century. One challenging aspect of documentation is to develop machine learning tools to automate the processing of EL audio via automatic speech recognition (ASR), machine translation (MT), or speech translation (ST). This paper presents an open-access speech translation corpus of Highland Puebla Nahuatl (glottocode high1278), an EL spoken in central Mexico. It then addresses machine learning contributions to endangered language documentation and argues for the importance of speech translation as a key element in the documentation process. In our experiments, we observed that state-of-the-art end-to-end ST models could outperform a cascaded ST (ASR {\textgreater} MT) pipeline when translating endangered language documentation materials.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2021-highland">
<titleInfo>
<title>Highland Puebla Nahuatl Speech Translation Corpus for Endangered Language Documentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiatong</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Amith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuankai</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Dalmia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinji</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Mager</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annette</namePart>
<namePart type="family">Rios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="given">Meza</namePart>
<namePart type="family">Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</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>Documentation of endangered languages (ELs) has become increasingly urgent as thousands of languages are on the verge of disappearing by the end of the 21st century. One challenging aspect of documentation is to develop machine learning tools to automate the processing of EL audio via automatic speech recognition (ASR), machine translation (MT), or speech translation (ST). This paper presents an open-access speech translation corpus of Highland Puebla Nahuatl (glottocode high1278), an EL spoken in central Mexico. It then addresses machine learning contributions to endangered language documentation and argues for the importance of speech translation as a key element in the documentation process. In our experiments, we observed that state-of-the-art end-to-end ST models could outperform a cascaded ST (ASR \textgreater MT) pipeline when translating endangered language documentation materials.</abstract>
<identifier type="citekey">shi-etal-2021-highland</identifier>
<identifier type="doi">10.18653/v1/2021.americasnlp-1.7</identifier>
<location>
<url>https://aclanthology.org/2021.americasnlp-1.7</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>53</start>
<end>63</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Highland Puebla Nahuatl Speech Translation Corpus for Endangered Language Documentation
%A Shi, Jiatong
%A Amith, Jonathan D.
%A Chang, Xuankai
%A Dalmia, Siddharth
%A Yan, Brian
%A Watanabe, Shinji
%Y Mager, Manuel
%Y Oncevay, Arturo
%Y Rios, Annette
%Y Ruiz, Ivan Vladimir Meza
%Y Palmer, Alexis
%Y Neubig, Graham
%Y Kann, Katharina
%S Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F shi-etal-2021-highland
%X Documentation of endangered languages (ELs) has become increasingly urgent as thousands of languages are on the verge of disappearing by the end of the 21st century. One challenging aspect of documentation is to develop machine learning tools to automate the processing of EL audio via automatic speech recognition (ASR), machine translation (MT), or speech translation (ST). This paper presents an open-access speech translation corpus of Highland Puebla Nahuatl (glottocode high1278), an EL spoken in central Mexico. It then addresses machine learning contributions to endangered language documentation and argues for the importance of speech translation as a key element in the documentation process. In our experiments, we observed that state-of-the-art end-to-end ST models could outperform a cascaded ST (ASR \textgreater MT) pipeline when translating endangered language documentation materials.
%R 10.18653/v1/2021.americasnlp-1.7
%U https://aclanthology.org/2021.americasnlp-1.7
%U https://doi.org/10.18653/v1/2021.americasnlp-1.7
%P 53-63
Markdown (Informal)
[Highland Puebla Nahuatl Speech Translation Corpus for Endangered Language Documentation](https://aclanthology.org/2021.americasnlp-1.7) (Shi et al., AmericasNLP 2021)
ACL