Dataset Open Access

Pairwise Learning using Unsupervised Bottleneck Features for Zero-Resource Speech Challenge 2017 (System 1)

Yougen Yuan; Cheung-Chi Leung; Lei Xie; Hongjie Chen; Bin Ma; Haizhou Li


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">pairwise learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">zero-resource</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">unsupervised bottleneck features</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">neural networks</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">autoencoder</subfield>
  </datafield>
  <controlfield tag="005">20190410041345.0</controlfield>
  <controlfield tag="001">814566</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Institute for Infocomm Research</subfield>
    <subfield code="a">Cheung-Chi Leung</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Northwestern Polytechnical University</subfield>
    <subfield code="a">Lei Xie</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Northwestern Polytechnical University</subfield>
    <subfield code="a">Hongjie Chen</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Institute for Infocomm Research</subfield>
    <subfield code="a">Bin Ma</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">National University of Singapore</subfield>
    <subfield code="a">Haizhou Li</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">8136374828</subfield>
    <subfield code="z">md5:52021927048d26ac14470c972c3ffb99</subfield>
    <subfield code="u">https://zenodo.org/record/814566/files/10_5281_zenodo_809197.tgz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">8136375943</subfield>
    <subfield code="z">md5:2948b438c9dcdae8e449378f260b3ce8</subfield>
    <subfield code="u">https://zenodo.org/record/814566/files/10_5281_zenodo_814566.tgz</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2017-06-15</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="p">user-zerospeech2017</subfield>
    <subfield code="o">oai:zenodo.org:814566</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Northwestern Polytechnical University</subfield>
    <subfield code="a">Yougen Yuan</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Pairwise Learning using Unsupervised Bottleneck Features for Zero-Resource Speech Challenge 2017 (System 1)</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-zerospeech2017</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">http://creativecommons.org/licenses/by-sa/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution Share Alike 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;The system is for track1 alone.  We trained an antoencoder using unsupervised bottleneck features with word-pair information from Switchboard. The unsupervised bottleneck features was extracted from an extractor of multi-task learning deep neural networks (MTL-DNN). The word-pair information was the ground truth from Switchboard. The final features are obtained from the third layer in our pairwise trained autoencoder.&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.809196</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.814566</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
55
5
views
downloads
All versions This version
Views 5539
Downloads 54
Data volume 40.7 GB32.5 GB
Unique views 5039
Unique downloads 32

Share

Cite as