@inproceedings{di-gangi-etal-2019-must,
title = "{M}u{ST}-{C}: a {M}ultilingual {S}peech {T}ranslation {C}orpus",
author = "Di Gangi, Mattia A. and
Cattoni, Roldano and
Bentivogli, Luisa and
Negri, Matteo and
Turchi, Marco",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1202",
doi = "10.18653/v1/N19-1202",
pages = "2012--2017",
abstract = "Current research on spoken language translation (SLT) has to confront with the scarcity of sizeable and publicly available training corpora. This problem hinders the adoption of neural end-to-end approaches, which represent the state of the art in the two parent tasks of SLT: automatic speech recognition and machine translation. To fill this gap, we created MuST-C, a multilingual speech translation corpus whose size and quality will facilitate the training of end-to-end systems for SLT from English into 8 languages. For each target language, MuST-C comprises at least 385 hours of audio recordings from English TED Talks, which are automatically aligned at the sentence level with their manual transcriptions and translations. Together with a description of the corpus creation methodology (scalable to add new data and cover new languages), we provide an empirical verification of its quality and SLT results computed with a state-of-the-art approach on each language direction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="di-gangi-etal-2019-must">
<titleInfo>
<title>MuST-C: a Multilingual Speech Translation Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mattia</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Di Gangi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roldano</namePart>
<namePart type="family">Cattoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Bentivogli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current research on spoken language translation (SLT) has to confront with the scarcity of sizeable and publicly available training corpora. This problem hinders the adoption of neural end-to-end approaches, which represent the state of the art in the two parent tasks of SLT: automatic speech recognition and machine translation. To fill this gap, we created MuST-C, a multilingual speech translation corpus whose size and quality will facilitate the training of end-to-end systems for SLT from English into 8 languages. For each target language, MuST-C comprises at least 385 hours of audio recordings from English TED Talks, which are automatically aligned at the sentence level with their manual transcriptions and translations. Together with a description of the corpus creation methodology (scalable to add new data and cover new languages), we provide an empirical verification of its quality and SLT results computed with a state-of-the-art approach on each language direction.</abstract>
<identifier type="citekey">di-gangi-etal-2019-must</identifier>
<identifier type="doi">10.18653/v1/N19-1202</identifier>
<location>
<url>https://aclanthology.org/N19-1202</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>2012</start>
<end>2017</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MuST-C: a Multilingual Speech Translation Corpus
%A Di Gangi, Mattia A.
%A Cattoni, Roldano
%A Bentivogli, Luisa
%A Negri, Matteo
%A Turchi, Marco
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F di-gangi-etal-2019-must
%X Current research on spoken language translation (SLT) has to confront with the scarcity of sizeable and publicly available training corpora. This problem hinders the adoption of neural end-to-end approaches, which represent the state of the art in the two parent tasks of SLT: automatic speech recognition and machine translation. To fill this gap, we created MuST-C, a multilingual speech translation corpus whose size and quality will facilitate the training of end-to-end systems for SLT from English into 8 languages. For each target language, MuST-C comprises at least 385 hours of audio recordings from English TED Talks, which are automatically aligned at the sentence level with their manual transcriptions and translations. Together with a description of the corpus creation methodology (scalable to add new data and cover new languages), we provide an empirical verification of its quality and SLT results computed with a state-of-the-art approach on each language direction.
%R 10.18653/v1/N19-1202
%U https://aclanthology.org/N19-1202
%U https://doi.org/10.18653/v1/N19-1202
%P 2012-2017
Markdown (Informal)
[MuST-C: a Multilingual Speech Translation Corpus](https://aclanthology.org/N19-1202) (Di Gangi et al., NAACL 2019)
ACL
- Mattia A. Di Gangi, Roldano Cattoni, Luisa Bentivogli, Matteo Negri, and Marco Turchi. 2019. MuST-C: a Multilingual Speech Translation Corpus. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2012–2017, Minneapolis, Minnesota. Association for Computational Linguistics.