<?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>2026-05-14T23:30:52Z</responseDate>
  <request metadataPrefix="jpcoar_1.0" verb="GetRecord" identifier="oai:ipsj.ixsq.nii.ac.jp:00218479">https://ipsj.ixsq.nii.ac.jp/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:ipsj.ixsq.nii.ac.jp:00218479</identifier>
        <datestamp>2025-01-19T15:08:54Z</datestamp>
        <setSpec>1164:5159:10869:10940</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>BERTを用いた音声翻訳のための音声認識結果訂正の検討</dc:title>
          <dc:title xml:lang="en">A Study of Speech Recognition Result Correction for Speech Translation Using BERT</dc:title>
          <jpcoar:creator>
            <jpcoar:creatorName>小椋, 忠志</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>藤本, 雅清</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>沈, 鵬</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>Lu, Xugang</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>河井, 恒</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Tadashi, Ogura</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Masakiyo, Fjimoto</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Peng, Shen</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Xugang, Lu</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Hisashi, Kawai</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:subject subjectScheme="Other">ポスターセッション1</jpcoar:subject>
          <datacite:description descriptionType="Other">音声認識と機械翻訳からなる音声翻訳技術においては，入り口となる音声認識の性能改善が重要である．しかし，単純な音声認識器の改善のみでは問題解決は難しく，音声認識結果に対する何らかの誤り訂正処理が必要である．そこで本研究では，近年注目を集めている巨大言語モデル BERT を用いた音声翻訳向けの音声認識結果訂正手法について検討した．提案手法では文脈を考慮した訂正を行うことができ，発話内容の「意味」や「意図」を違えることを軽減した高精度な音声翻訳結果を得ることができる．</datacite:description>
          <datacite:description descriptionType="Other">Speech translation (ST) technology consists of automatic speech recognition (ASR) and machine translation technologies. Since ASR is the ﬁrst module to be processed in ST, improving ASR performance is a critical factor in ST. However, it is diﬃcult to solve this problem by pursuing only improvement of ASR performance, and error correction processing for ASR results is strongly required. Therefore, in this paper, we propose an error correction method for ASR results to improve ST performance using the state-of-the-art huge scale language model, BERT. The proposed method realizes context-aware error correction for ASR results, and successfully improves the accuracy of ST by reducing misunderstandings of “meaning" and "intention" of utterances.</datacite:description>
          <dc:publisher xml:lang="ja">情報処理学会</dc:publisher>
          <datacite:date dateType="Issued">2022-06-10</datacite:date>
          <dc:language>jpn</dc:language>
          <dc:type rdf:resource="http://purl.org/coar/resource_type/c_18gh">technical report</dc:type>
          <jpcoar:identifier identifierType="URI">https://ipsj.ixsq.nii.ac.jp/records/218479</jpcoar:identifier>
          <jpcoar:sourceIdentifier identifierType="ISSN">2188-8663</jpcoar:sourceIdentifier>
          <jpcoar:sourceIdentifier identifierType="NCID">AN10442647</jpcoar:sourceIdentifier>
          <jpcoar:sourceTitle>研究報告音声言語情報処理（SLP）</jpcoar:sourceTitle>
          <jpcoar:volume>2022-SLP-142</jpcoar:volume>
          <jpcoar:issue>20</jpcoar:issue>
          <jpcoar:pageStart>1</jpcoar:pageStart>
          <jpcoar:pageEnd>4</jpcoar:pageEnd>
          <jpcoar:file>
            <jpcoar:URI label="IPSJ-SLP22142020.pdf">https://ipsj.ixsq.nii.ac.jp/record/218479/files/IPSJ-SLP22142020.pdf</jpcoar:URI>
            <jpcoar:mimeType>application/pdf</jpcoar:mimeType>
            <jpcoar:extent>1.6 MB</jpcoar:extent>
          </jpcoar:file>
        </jpcoar:jpcoar>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
