@inproceedings{inaguma-etal-2018-jhu,
title = "The {JHU}/{K}yoto{U} Speech Translation System for {IWSLT} 2018",
author = "Inaguma, Hirofumi and
Zhang, Xuan and
Wang, Zhiqi and
Renduchintala, Adithya and
Watanabe, Shinji and
Duh, Kevin",
editor = "Turchi, Marco and
Niehues, Jan and
Frederico, Marcello",
booktitle = "Proceedings of the 15th International Conference on Spoken Language Translation",
month = oct # " 29-30",
year = "2018",
address = "Brussels",
publisher = "International Conference on Spoken Language Translation",
url = "https://aclanthology.org/2018.iwslt-1.23/",
pages = "153--159",
abstract = "This paper describes the Johns Hopkins University (JHU) and Kyoto University submissions to the Speech Translation evaluation campaign at IWSLT2018. Our end-to-end speech translation systems are based on ESPnet and implements an attention-based encoder-decoder model. As comparison, we also experiment with a pipeline system that uses independent neural network systems for both the speech transcription and text translation components. We find that a transfer learning approach that bootstraps the end-to-end speech translation system with speech transcription system`s parameters is important for training on small datasets."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="inaguma-etal-2018-jhu">
<titleInfo>
<title>The JHU/KyotoU Speech Translation System for IWSLT 2018</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hirofumi</namePart>
<namePart type="family">Inaguma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adithya</namePart>
<namePart type="family">Renduchintala</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>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct 29-30</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Spoken Language Translation</title>
</titleInfo>
<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">Jan</namePart>
<namePart type="family">Niehues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Frederico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Conference on Spoken Language Translation</publisher>
<place>
<placeTerm type="text">Brussels</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the Johns Hopkins University (JHU) and Kyoto University submissions to the Speech Translation evaluation campaign at IWSLT2018. Our end-to-end speech translation systems are based on ESPnet and implements an attention-based encoder-decoder model. As comparison, we also experiment with a pipeline system that uses independent neural network systems for both the speech transcription and text translation components. We find that a transfer learning approach that bootstraps the end-to-end speech translation system with speech transcription system‘s parameters is important for training on small datasets.</abstract>
<identifier type="citekey">inaguma-etal-2018-jhu</identifier>
<location>
<url>https://aclanthology.org/2018.iwslt-1.23/</url>
</location>
<part>
<date>2018-oct 29-30</date>
<extent unit="page">
<start>153</start>
<end>159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The JHU/KyotoU Speech Translation System for IWSLT 2018
%A Inaguma, Hirofumi
%A Zhang, Xuan
%A Wang, Zhiqi
%A Renduchintala, Adithya
%A Watanabe, Shinji
%A Duh, Kevin
%Y Turchi, Marco
%Y Niehues, Jan
%Y Frederico, Marcello
%S Proceedings of the 15th International Conference on Spoken Language Translation
%D 2018
%8 oct 29 30
%I International Conference on Spoken Language Translation
%C Brussels
%F inaguma-etal-2018-jhu
%X This paper describes the Johns Hopkins University (JHU) and Kyoto University submissions to the Speech Translation evaluation campaign at IWSLT2018. Our end-to-end speech translation systems are based on ESPnet and implements an attention-based encoder-decoder model. As comparison, we also experiment with a pipeline system that uses independent neural network systems for both the speech transcription and text translation components. We find that a transfer learning approach that bootstraps the end-to-end speech translation system with speech transcription system‘s parameters is important for training on small datasets.
%U https://aclanthology.org/2018.iwslt-1.23/
%P 153-159
Markdown (Informal)
[The JHU/KyotoU Speech Translation System for IWSLT 2018](https://aclanthology.org/2018.iwslt-1.23/) (Inaguma et al., IWSLT 2018)
ACL
- Hirofumi Inaguma, Xuan Zhang, Zhiqi Wang, Adithya Renduchintala, Shinji Watanabe, and Kevin Duh. 2018. The JHU/KyotoU Speech Translation System for IWSLT 2018. In Proceedings of the 15th International Conference on Spoken Language Translation, pages 153–159, Brussels. International Conference on Spoken Language Translation.