@inproceedings{beilharz-etal-2020-librivoxdeen,
title = "{L}ibri{V}ox{D}e{E}n: A Corpus for {G}erman-to-{E}nglish Speech Translation and {G}erman Speech Recognition",
author = "Beilharz, Benjamin and
Sun, Xin and
Karimova, Sariya and
Riezler, Stefan",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.441",
pages = "3590--3594",
abstract = "We present a corpus of sentence-aligned triples of German audio, German text, and English translation, based on German audio books. The speech translation data consist of 110 hours of audio material aligned to over 50k parallel sentences. An even larger dataset comprising 547 hours of German speech aligned to German text is available for speech recognition. The audio data is read speech and thus low in disfluencies. The quality of audio and sentence alignments has been checked by a manual evaluation, showing that speech alignment quality is in general very high. The sentence alignment quality is comparable to well-used parallel translation data and can be adjusted by cutoffs on the automatic alignment score. To our knowledge, this corpus is to date the largest resource for German speech recognition and for end-to-end German-to-English speech translation.",
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="beilharz-etal-2020-librivoxdeen">
<titleInfo>
<title>LibriVoxDeEn: A Corpus for German-to-English Speech Translation and German Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Beilharz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sariya</namePart>
<namePart type="family">Karimova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Riezler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</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 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<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>We present a corpus of sentence-aligned triples of German audio, German text, and English translation, based on German audio books. The speech translation data consist of 110 hours of audio material aligned to over 50k parallel sentences. An even larger dataset comprising 547 hours of German speech aligned to German text is available for speech recognition. The audio data is read speech and thus low in disfluencies. The quality of audio and sentence alignments has been checked by a manual evaluation, showing that speech alignment quality is in general very high. The sentence alignment quality is comparable to well-used parallel translation data and can be adjusted by cutoffs on the automatic alignment score. To our knowledge, this corpus is to date the largest resource for German speech recognition and for end-to-end German-to-English speech translation.</abstract>
<identifier type="citekey">beilharz-etal-2020-librivoxdeen</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.441</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>3590</start>
<end>3594</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LibriVoxDeEn: A Corpus for German-to-English Speech Translation and German Speech Recognition
%A Beilharz, Benjamin
%A Sun, Xin
%A Karimova, Sariya
%A Riezler, Stefan
%S Proceedings of the 12th 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 beilharz-etal-2020-librivoxdeen
%X We present a corpus of sentence-aligned triples of German audio, German text, and English translation, based on German audio books. The speech translation data consist of 110 hours of audio material aligned to over 50k parallel sentences. An even larger dataset comprising 547 hours of German speech aligned to German text is available for speech recognition. The audio data is read speech and thus low in disfluencies. The quality of audio and sentence alignments has been checked by a manual evaluation, showing that speech alignment quality is in general very high. The sentence alignment quality is comparable to well-used parallel translation data and can be adjusted by cutoffs on the automatic alignment score. To our knowledge, this corpus is to date the largest resource for German speech recognition and for end-to-end German-to-English speech translation.
%U https://aclanthology.org/2020.lrec-1.441
%P 3590-3594
Markdown (Informal)
[LibriVoxDeEn: A Corpus for German-to-English Speech Translation and German Speech Recognition](https://aclanthology.org/2020.lrec-1.441) (Beilharz et al., LREC 2020)
ACL