Conference paper Open Access

On Using SpecAugment for End-to-End Speech Translation

Bahar, Parnia; Zeyer, Albert; Schlüter, Ralf; Ney, Hermann


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">20200120164430.0</controlfield>
  <controlfield tag="001">3525010</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Human Language Technology and Pattern Recognition Group Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany &amp;  AppTek, 52062 Aachen, Germany</subfield>
    <subfield code="a">Zeyer, Albert</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Human Language Technology and Pattern Recognition Group, Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany</subfield>
    <subfield code="a">Schlüter, Ralf</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Human Language Technology and Pattern Recognition Group Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany &amp;  AppTek, 52062 Aachen, Germany</subfield>
    <subfield code="a">Ney, Hermann</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">768990</subfield>
    <subfield code="z">md5:b101a778188679cfbdd072bdb714062c</subfield>
    <subfield code="u">https://zenodo.org/record/3525010/files/IWSLT2019_paper_19.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:3525010</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Human Language Technology and Pattern Recognition Group Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany &amp;  AppTek, 52062 Aachen, Germany</subfield>
    <subfield code="a">Bahar, Parnia</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">On Using SpecAugment for End-to-End Speech Translation</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;This work investigates a simple data augmentation technique, SpecAugment, for end-to-end speech translation. SpecAugment is a low-cost implementation method applied directly to the audio input features and it consists of masking blocks of frequency channels, and/or time steps. We apply SpecAugment on end-to-end speech translation tasks and achieve up to +2.2% BLEU&amp;nbsp;on LibriSpeech Audiobooks En&amp;rarr;Fr and +1.2% on IWSLT TED-talks En&amp;rarr;De by alleviating overfitting to some extent. We also examine the effectiveness of the method in a variety of data scenarios and show that the method also leads to significant improvements in various data conditions irrespective of the amount of training data.&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.3525009</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3525010</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
100
76
views
downloads
All versions This version
Views 10098
Downloads 7676
Data volume 58.4 MB58.4 MB
Unique views 8785
Unique downloads 6666

Share

Cite as