<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="inaguma-etal-2019-espnet">
    <titleInfo>
        <title>ESPnet How2 Speech Translation System for IWSLT 2019: Pre-training, Knowledge Distillation, and Going Deeper</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">Shun</namePart>
        <namePart type="family">Kiyono</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nelson</namePart>
        <namePart type="given">Enrique</namePart>
        <namePart type="given">Yalta</namePart>
        <namePart type="family">Soplin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jun</namePart>
        <namePart type="family">Suzuki</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>
    <name type="personal">
        <namePart type="given">Shinji</namePart>
        <namePart type="family">Watanabe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-nov&quot; 2-3&quot;</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 16th International Conference on Spoken Language Translation</title>
        </titleInfo>
        <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 the ESPnet submissions to the How2 Speech Translation task at IWSLT2019. In this year, we mainly build our systems based on Transformer architectures in all tasks and focus on the end-to-end speech translation (E2E-ST). We first compare RNN-based models and Transformer, and then confirm Transformer models significantly and consistently outperform RNN models in all tasks and corpora. Next, we investigate pre-training of E2E-ST models with the ASR and MT tasks. On top of the pre-training, we further explore knowledge distillation from the NMT model and the deeper speech encoder, and confirm drastic improvements over the baseline model. All of our codes are publicly available in ESPnet.</abstract>
    <identifier type="citekey">inaguma-etal-2019-espnet</identifier>
    <location>
        <url>https://aclanthology.org/2019.iwslt-1.4</url>
    </location>
    <part>
        <date>2019-nov&quot; 2-3&quot;</date>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ESPnet How2 Speech Translation System for IWSLT 2019: Pre-training, Knowledge Distillation, and Going Deeper
%A Inaguma, Hirofumi
%A Kiyono, Shun
%A Soplin, Nelson Enrique Yalta
%A Suzuki, Jun
%A Duh, Kevin
%A Watanabe, Shinji
%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 inaguma-etal-2019-espnet
%X This paper describes the ESPnet submissions to the How2 Speech Translation task at IWSLT2019. In this year, we mainly build our systems based on Transformer architectures in all tasks and focus on the end-to-end speech translation (E2E-ST). We first compare RNN-based models and Transformer, and then confirm Transformer models significantly and consistently outperform RNN models in all tasks and corpora. Next, we investigate pre-training of E2E-ST models with the ASR and MT tasks. On top of the pre-training, we further explore knowledge distillation from the NMT model and the deeper speech encoder, and confirm drastic improvements over the baseline model. All of our codes are publicly available in ESPnet.
%U https://aclanthology.org/2019.iwslt-1.4

Markdown (Informal)

[ESPnet How2 Speech Translation System for IWSLT 2019: Pre-training, Knowledge Distillation, and Going Deeper](https://aclanthology.org/2019.iwslt-1.4) (Inaguma et al., IWSLT 2019)

• ESPnet How2 Speech Translation System for IWSLT 2019: Pre-training, Knowledge Distillation, and Going Deeper (Inaguma et al., IWSLT 2019)

ACL

• Hirofumi Inaguma, Shun Kiyono, Nelson Enrique Yalta Soplin, Jun Suzuki, Kevin Duh, and Shinji Watanabe. 2019. ESPnet How2 Speech Translation System for IWSLT 2019: Pre-training, Knowledge Distillation, and Going Deeper. In Proceedings of the 16th International Conference on Spoken Language Translation, Hong Kong. Association for Computational Linguistics.