Conference paper Open Access

Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training

Cheng, Qiao; Fan, Meiyuan; Han, Yaqian; Huang, Jin; Duan, Yitao


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.3524969</identifier>
  <creators>
    <creator>
      <creatorName>Cheng, Qiao</creatorName>
      <givenName>Qiao</givenName>
      <familyName>Cheng</familyName>
      <affiliation>NetEase Youdao Information Technology (Beijing) Co., LTD., Beijing, China</affiliation>
    </creator>
    <creator>
      <creatorName>Fan, Meiyuan</creatorName>
      <givenName>Meiyuan</givenName>
      <familyName>Fan</familyName>
      <affiliation>NetEase Youdao Information Technology (Beijing) Co., LTD., Beijing, China</affiliation>
    </creator>
    <creator>
      <creatorName>Han, Yaqian</creatorName>
      <givenName>Yaqian</givenName>
      <familyName>Han</familyName>
      <affiliation>NetEase Youdao Information Technology (Beijing) Co., LTD., Beijing, China</affiliation>
    </creator>
    <creator>
      <creatorName>Huang, Jin</creatorName>
      <givenName>Jin</givenName>
      <familyName>Huang</familyName>
      <affiliation>NetEase Youdao Information Technology (Beijing) Co., LTD., Beijing, ChinaNetEase Youdao Information Technology (Beijing) Co., LTD., Beijing, China</affiliation>
    </creator>
    <creator>
      <creatorName>Duan, Yitao</creatorName>
      <givenName>Yitao</givenName>
      <familyName>Duan</familyName>
      <affiliation>NetEase Youdao Information Technology (Beijing) Co., LTD., Beijing, China</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2019</publicationYear>
  <dates>
    <date dateType="Issued">2019-11-02</date>
  </dates>
  <resourceType resourceTypeGeneral="Text">Conference paper</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3524969</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3524968</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/iwslt2019</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel corpus composed of clean text and will perform poorly on text with recognition noise, a gap well known in speech translation community. In this paper, we propose a training architecture which aims at making a neural machine translation model more robust against speech recognition errors. Our approach addresses the encoder and the decoder simultaneously using adversarial learning and data augmentation, respectively. Experimental results on IWSLT2018 speech translation task show that our approach can bridge the gap between the ASR output and the MT input, outperforms the baseline by up to 2.83 BLEU on noisy ASR output, while maintaining close performance on clean text.&lt;/p&gt;</description>
  </descriptions>
</resource>
136
109
views
downloads
All versions This version
Views 136137
Downloads 109109
Data volume 43.6 MB43.6 MB
Unique views 120121
Unique downloads 9393

Share

Cite as