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


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <controlfield tag="005">20200120171802.0</controlfield>
  <controlfield tag="001">3524969</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">NetEase Youdao Information Technology (Beijing) Co., LTD., Beijing, China</subfield>
    <subfield code="a">Fan, Meiyuan</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">NetEase Youdao Information Technology (Beijing) Co., LTD., Beijing, China</subfield>
    <subfield code="a">Han, Yaqian</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">NetEase Youdao Information Technology (Beijing) Co., LTD., Beijing, ChinaNetEase Youdao Information Technology (Beijing) Co., LTD., Beijing, China</subfield>
    <subfield code="a">Huang, Jin</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">NetEase Youdao Information Technology (Beijing) Co., LTD., Beijing, China</subfield>
    <subfield code="a">Duan, Yitao</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">400196</subfield>
    <subfield code="z">md5:36e0bc7ac948b105985ffc27839fe087</subfield>
    <subfield code="u">https://zenodo.org/record/3524969/files/IWSLT2019_paper_6.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-11-02</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-iwslt2019</subfield>
    <subfield code="o">oai:zenodo.org:3524969</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">NetEase Youdao Information Technology (Beijing) Co., LTD., Beijing, China</subfield>
    <subfield code="a">Cheng, Qiao</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-iwslt2019</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&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;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3524968</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3524969</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
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