@inproceedings{nguyen-etal-2021-kits,
title = "{KIT}`s {IWSLT} 2021 Offline Speech Translation System",
author = {Nguyen, Tuan Nam and
Nguyen, Thai Son and
Huber, Christian and
Pham, Ngoc-Quan and
Ha, Thanh-Le and
Schneider, Felix and
St{\"u}ker, Sebastian},
editor = "Federico, Marcello and
Waibel, Alex and
Costa-juss{\`a}, Marta R. and
Niehues, Jan and
Stuker, Sebastian and
Salesky, Elizabeth",
booktitle = "Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)",
month = aug,
year = "2021",
address = "Bangkok, Thailand (online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.iwslt-1.13/",
doi = "10.18653/v1/2021.iwslt-1.13",
pages = "125--130",
abstract = "This paper describes KIT`submission to the IWSLT 2021 Offline Speech Translation Task. We describe a system in both cascaded condition and end-to-end condition. In the cascaded condition, we investigated different end-to-end architectures for the speech recognition module. For the text segmentation module, we trained a small transformer-based model on high-quality monolingual data. For the translation module, our last year`s neural machine translation model was reused. In the end-to-end condition, we improved our Speech Relative Transformer architecture to reach or even surpass the result of the cascade system."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2021-kits">
<titleInfo>
<title>KIT‘s IWSLT 2021 Offline Speech Translation System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tuan</namePart>
<namePart type="given">Nam</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thai</namePart>
<namePart type="given">Son</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Huber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngoc-Quan</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanh-Le</namePart>
<namePart type="family">Ha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stüker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Sebastian</namePart>
<namePart type="family">Stuker</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes KIT‘submission to the IWSLT 2021 Offline Speech Translation Task. We describe a system in both cascaded condition and end-to-end condition. In the cascaded condition, we investigated different end-to-end architectures for the speech recognition module. For the text segmentation module, we trained a small transformer-based model on high-quality monolingual data. For the translation module, our last year‘s neural machine translation model was reused. In the end-to-end condition, we improved our Speech Relative Transformer architecture to reach or even surpass the result of the cascade system.</abstract>
<identifier type="citekey">nguyen-etal-2021-kits</identifier>
<identifier type="doi">10.18653/v1/2021.iwslt-1.13</identifier>
<location>
<url>https://aclanthology.org/2021.iwslt-1.13/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>125</start>
<end>130</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KIT‘s IWSLT 2021 Offline Speech Translation System
%A Nguyen, Tuan Nam
%A Nguyen, Thai Son
%A Huber, Christian
%A Pham, Ngoc-Quan
%A Ha, Thanh-Le
%A Schneider, Felix
%A Stüker, Sebastian
%Y Federico, Marcello
%Y Waibel, Alex
%Y Costa-jussà, Marta R.
%Y Niehues, Jan
%Y Stuker, Sebastian
%Y Salesky, Elizabeth
%S Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (online)
%F nguyen-etal-2021-kits
%X This paper describes KIT‘submission to the IWSLT 2021 Offline Speech Translation Task. We describe a system in both cascaded condition and end-to-end condition. In the cascaded condition, we investigated different end-to-end architectures for the speech recognition module. For the text segmentation module, we trained a small transformer-based model on high-quality monolingual data. For the translation module, our last year‘s neural machine translation model was reused. In the end-to-end condition, we improved our Speech Relative Transformer architecture to reach or even surpass the result of the cascade system.
%R 10.18653/v1/2021.iwslt-1.13
%U https://aclanthology.org/2021.iwslt-1.13/
%U https://doi.org/10.18653/v1/2021.iwslt-1.13
%P 125-130
Markdown (Informal)
[KIT’s IWSLT 2021 Offline Speech Translation System](https://aclanthology.org/2021.iwslt-1.13/) (Nguyen et al., IWSLT 2021)
ACL
- Tuan Nam Nguyen, Thai Son Nguyen, Christian Huber, Ngoc-Quan Pham, Thanh-Le Ha, Felix Schneider, and Sebastian Stüker. 2021. KIT’s IWSLT 2021 Offline Speech Translation System. In Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021), pages 125–130, Bangkok, Thailand (online). Association for Computational Linguistics.