1 Ocak 2019 Konferans bildirisi Açık Erişim

Uslu, Zeynep Gulhan; Yildirim, Tulay

MARC21 XML

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">user-tubitak-adresli-yayinlar</subfield>
    <subfield code="o">oai:zenodo.org:99851</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">In this paper, we investigate the effects of data augmentation and adding out of domain data on Turkish spontaneous speech recognition. We apply different acoustic model training techniques including Gaussian Mixture Models, Deep Neural Network and Time Delay Neural Network to Babel Turkish spontaneous telephone speech data. We find that Time Delay Neural Network with iVectors based acoustic model performs the best result. We demonstrate the effect of data augmentation by adding speed and volume perturbation applied data in training. We investigate the effect of increasing acoustic model training data by including two call center data. We increase training data by adding about 100 hours of modified out of domain broadcast data. We also examine the effect of neural network based language modeling techniques like Recurrent Neural Network language models.</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="a">2019 16TH INTERNATIONAL MULTI-CONFERENCE ON SYSTEMS, SIGNALS &amp; DEVICES (SSD)</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="a">Creative Commons Attribution</subfield>
    <subfield code="u">http://www.opendefinition.org/licenses/cc-by</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.81043/aperta.99850</subfield>
    <subfield code="n">doi</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="a">Uslu, Zeynep Gulhan</subfield>
    <subfield code="u">Yildiz Tech Univ, TUBITAK BILGEM, Elect &amp; Commun Engn Dept, Istanbul, Turkey</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="z">md5:d4c8b28695e355d1096c1d95e699b387</subfield>
    <subfield code="s">202</subfield>
    <subfield code="u">https://aperta.ulakbim.gov.trrecord/99851/files/bib-ed79b1b8-0801-42ce-9379-b55dce7d9eed.txt</subfield>
  </datafield>
  <controlfield tag="005">20210316141813.0</controlfield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-01-01</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.81043/aperta.99851</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Improving Turkish Telephone Speech Recognition with Data Augmentation and Out of Domain Data</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Yildirim, Tulay</subfield>
    <subfield code="u">Yildiz Tech Univ, Elect &amp; Commun Engn Dept, Istanbul, Turkey</subfield>
  </datafield>
  <controlfield tag="001">99851</controlfield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-tubitak-adresli-yayinlar</subfield>
  </datafield>
</record>