@inproceedings{tu-etal-2019-end,
title = "End-to-end Speech Translation System Description of {LIT} for {IWSLT} 2019",
author = "Tu, Mei and
Liu, Wei and
Wang, Lijie and
Chen, Xiao and
Wen, Xue",
editor = {Niehues, Jan and
Cattoni, Rolando and
St{\"u}ker, Sebastian and
Negri, Matteo and
Turchi, Marco and
Ha, Thanh-Le and
Salesky, Elizabeth and
Sanabria, Ramon and
Barrault, Loic and
Specia, Lucia and
Federico, Marcello},
booktitle = "Proceedings of the 16th International Conference on Spoken Language Translation",
month = nov # " 2-3",
year = "2019",
address = "Hong Kong",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2019.iwslt-1.7",
abstract = "This paper describes our end-to-end speech translation system for the speech translation task of lectures and TED talks from English to German for IWSLT Evaluation 2019. We propose layer-tied self-attention for end-to-end speech translation. Our method takes advantage of sharing weights of speech encoder and text decoder. The representation of source speech and the representation of target text are coordinated layer by layer, so that the speech and text can learn a better alignment during the training procedure. We also adopt data augmentation to enhance the parallel speech-text corpus. The En-De experimental results show that our best model achieves 17.68 on tst2015. Our ASR achieves WER of 6.6{\%} on TED-LIUM test set. The En-Pt model can achieve about 11.83 on the MuST-C dev set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tu-etal-2019-end">
<titleInfo>
<title>End-to-end Speech Translation System Description of LIT for IWSLT 2019</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lijie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xue</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-nov 2-3</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Conference on Spoken Language Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rolando</namePart>
<namePart type="family">Cattoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stüker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanh-Le</namePart>
<namePart type="family">Ha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramon</namePart>
<namePart type="family">Sanabria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Loic</namePart>
<namePart type="family">Barrault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our end-to-end speech translation system for the speech translation task of lectures and TED talks from English to German for IWSLT Evaluation 2019. We propose layer-tied self-attention for end-to-end speech translation. Our method takes advantage of sharing weights of speech encoder and text decoder. The representation of source speech and the representation of target text are coordinated layer by layer, so that the speech and text can learn a better alignment during the training procedure. We also adopt data augmentation to enhance the parallel speech-text corpus. The En-De experimental results show that our best model achieves 17.68 on tst2015. Our ASR achieves WER of 6.6% on TED-LIUM test set. The En-Pt model can achieve about 11.83 on the MuST-C dev set.</abstract>
<identifier type="citekey">tu-etal-2019-end</identifier>
<location>
<url>https://aclanthology.org/2019.iwslt-1.7</url>
</location>
<part>
<date>2019-nov 2-3</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T End-to-end Speech Translation System Description of LIT for IWSLT 2019
%A Tu, Mei
%A Liu, Wei
%A Wang, Lijie
%A Chen, Xiao
%A Wen, Xue
%Y Niehues, Jan
%Y Cattoni, Rolando
%Y Stüker, Sebastian
%Y Negri, Matteo
%Y Turchi, Marco
%Y Ha, Thanh-Le
%Y Salesky, Elizabeth
%Y Sanabria, Ramon
%Y Barrault, Loic
%Y Specia, Lucia
%Y Federico, Marcello
%S Proceedings of the 16th International Conference on Spoken Language Translation
%D 2019
%8 nov 2 3
%I Association for Computational Linguistics
%C Hong Kong
%F tu-etal-2019-end
%X This paper describes our end-to-end speech translation system for the speech translation task of lectures and TED talks from English to German for IWSLT Evaluation 2019. We propose layer-tied self-attention for end-to-end speech translation. Our method takes advantage of sharing weights of speech encoder and text decoder. The representation of source speech and the representation of target text are coordinated layer by layer, so that the speech and text can learn a better alignment during the training procedure. We also adopt data augmentation to enhance the parallel speech-text corpus. The En-De experimental results show that our best model achieves 17.68 on tst2015. Our ASR achieves WER of 6.6% on TED-LIUM test set. The En-Pt model can achieve about 11.83 on the MuST-C dev set.
%U https://aclanthology.org/2019.iwslt-1.7
Markdown (Informal)
[End-to-end Speech Translation System Description of LIT for IWSLT 2019](https://aclanthology.org/2019.iwslt-1.7) (Tu et al., IWSLT 2019)
ACL