<?xml version='1.0' encoding='UTF-8'?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-05-20T13:31:42Z</responseDate>
  <request verb="GetRecord" metadataPrefix="jpcoar_1.0" identifier="oai:ipsj.ixsq.nii.ac.jp:00108570">https://ipsj.ixsq.nii.ac.jp/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:ipsj.ixsq.nii.ac.jp:00108570</identifier>
        <datestamp>2025-01-21T08:44:55Z</datestamp>
        <setSpec>6504:6505:7806</setSpec>
      </header>
      <metadata>
        <jpcoar:jpcoar xmlns:datacite="https://schema.datacite.org/meta/kernel-4/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcndl="http://ndl.go.jp/dcndl/terms/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:jpcoar="https://github.com/JPCOAR/schema/blob/master/1.0/" xmlns:oaire="http://namespace.openaire.eu/schema/oaire/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:rioxxterms="http://www.rioxx.net/schema/v2.0/rioxxterms/" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns="https://github.com/JPCOAR/schema/blob/master/1.0/" xsi:schemaLocation="https://github.com/JPCOAR/schema/blob/master/1.0/jpcoar_scm.xsd">
          <dc:title>Audio-visual musical instrument recognition</dc:title>
          <jpcoar:creator>
            <jpcoar:creatorName>AngelicaLim</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>中村圭佑</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>中臺一博</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>尾形哲也</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>奥乃博</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:subject subjectScheme="Other">人工知能と認知科学</jpcoar:subject>
          <datacite:description descriptionType="Other">Is this person playing a violin or a flute? Classification of musical instrument performances is usually carried out using audio features such as spectral coefficients. We propose augmenting the typical audio feature set with visual features. We show that a combination of audio features and video perform better than audio alone, and verify this multimodal recognition approach on a real-time robot platform.</datacite:description>
          <dc:publisher xml:lang="ja">情報処理学会</dc:publisher>
          <datacite:date dateType="Issued">2011-03-02</datacite:date>
          <dc:language>eng</dc:language>
          <dc:type rdf:resource="http://purl.org/coar/resource_type/c_5794">conference paper</dc:type>
          <jpcoar:identifier identifierType="URI">https://ipsj.ixsq.nii.ac.jp/records/108570</jpcoar:identifier>
          <jpcoar:sourceIdentifier identifierType="NCID">AN00349328</jpcoar:sourceIdentifier>
          <jpcoar:sourceTitle>第73回全国大会講演論文集</jpcoar:sourceTitle>
          <jpcoar:volume>2011</jpcoar:volume>
          <jpcoar:issue>1</jpcoar:issue>
          <jpcoar:pageStart>309</jpcoar:pageStart>
          <jpcoar:pageEnd>310</jpcoar:pageEnd>
          <jpcoar:file>
            <jpcoar:URI>https://ipsj.ixsq.nii.ac.jp/record/108570/files/IPSJ-Z73-5R-9.pdf</jpcoar:URI>
            <jpcoar:mimeType>application/pdf</jpcoar:mimeType>
            <jpcoar:extent>928.8 kB</jpcoar:extent>
            <datacite:date dateType="Available">2014-12-17</datacite:date>
          </jpcoar:file>
        </jpcoar:jpcoar>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
