{
  "$schema": "/api/schemas/documents.schema.json",
  "apiVersion": "1.0.0",
  "generatedAt": "2026-06-17T23:49:39.838Z",
  "sourcePath": "src/main/data/docs",
  "docId": "10.5594-j18370XY",
  "document": {
    "abbrevTitle": "SMPTE Mot. Imag. J",
    "abbrevTitle$meta": {
      "confidence": "high",
      "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "abstract": "The British Broadcasting Corp. (BBC) manually tags recent programs on its website. Editors draw and assign these tags from open datasets made available within the Linked Data cloud, but this is a time-consuming process. Aside from recent programming, which is tagged, the BBC has a large radio archive that is untagged. Thus the possibility of automatically assigning tags to programs in a reasonable amount of time has been investigated. Tags enable a variety of use cases, such as dynamic building of topical aggregations, retrieval through topic-based search, or cross-domain navigation. Automatic tagging of archive content would ensure archive programs are as findable as recent programs. It would mean that topic-based collections of archive content can be easily built, for example, to find archive content that relates to current news events. This paper describes an infrastructure to process large program archives in a cost-effective and scalable manner using Amazon Web Services. An automated tagging algorithm using speech audio as an input is described. The paper also explains how this algorithm can be separated and distributed and how the workflow can be managed robustly, ensuring appropriate error handling, resource monitoring, and data management on a large scale. Finally, the results from processing the BBC World Service English-speaking audio archive are presented.",
    "abstract$meta": {
      "confidence": "high",
      "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "articleType": "orig-research",
    "articleType$meta": {
      "confidence": "high",
      "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "authors": [
      "Y. Raimond",
      "C. Lowis",
      "R. Hodgson",
      "D. Tinley"
    ],
    "authors$meta": {
      "confidence": "high",
      "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "copyright": {
      "holder": "Society of Motion Picture and Television Engineers, Inc.",
      "holder$meta": {
        "confidence": "high",
        "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
        "source": "parsed",
        "updated": "2026-05-22T23:54:08.922Z",
        "version": "smpte-journal-issue-xml@v1"
      },
      "year": "2014",
      "year$meta": {
        "confidence": "high",
        "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
        "source": "parsed",
        "updated": "2026-05-22T23:54:08.922Z",
        "version": "smpte-journal-issue-xml@v1"
      }
    },
    "copyright$meta": {
      "confidence": "high",
      "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "docId": "10.5594-j18370XY",
    "docId$meta": {
      "confidence": "high",
      "note": "Derived from DOI 10.5594/j18370XY",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "docLabel": "SMPTE Motion Imaging Journal ( Volume: 123, Issue: 1, 2014)",
    "docLabel$meta": {
      "confidence": "medium",
      "note": "Composed from journal title, volume, issue and date",
      "source": "inferred",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "docTitle": "Automated Metadata Enrichment of Large Speech Radio Archives",
    "docTitle$meta": {
      "confidence": "high",
      "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "docType": "Journal Article",
    "docType$meta": {
      "confidence": "high",
      "note": "journal_metadata XML — SMPTE journal paper",
      "source": "inferred",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "doi": "10.5594/j18370XY",
    "doi$meta": {
      "confidence": "high",
      "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "href": "https://doi.org/10.5594/j18370XY",
    "href$meta": {
      "confidence": "high",
      "note": "Constructed from DOI 10.5594/j18370XY",
      "source": "inferred",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "issn": {
      "print": "1545-0279",
      "print$meta": {
        "confidence": "high",
        "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
        "source": "parsed",
        "updated": "2026-05-22T23:54:08.922Z",
        "version": "smpte-journal-issue-xml@v1"
      }
    },
    "issn$meta": {
      "confidence": "high",
      "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "journalAcronym": "MIJR",
    "journalAcronym$meta": {
      "confidence": "high",
      "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "number": "1",
    "number$meta": {
      "confidence": "high",
      "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "pages": "35–41",
    "pages$meta": {
      "confidence": "high",
      "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "publicationDate": "2014-01-01",
    "publicationDate$meta": {
      "confidence": "low",
      "note": "Month/day absent in source — padded to 01-01",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "publisher": "SMPTE",
    "publisher$meta": {
      "confidence": "high",
      "note": "Normalised to registry \"SMPTE\" convention from publisher-name (SMPTE)",
      "source": "inferred",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "publisherLocation": {
      "city": "White Plains, NY",
      "city$meta": {
        "confidence": "high",
        "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
        "source": "parsed",
        "updated": "2026-05-22T23:54:08.922Z",
        "version": "smpte-journal-issue-xml@v1"
      },
      "country": "USA",
      "country$meta": {
        "confidence": "high",
        "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
        "source": "parsed",
        "updated": "2026-05-22T23:54:08.922Z",
        "version": "smpte-journal-issue-xml@v1"
      }
    },
    "publisherLocation$meta": {
      "confidence": "high",
      "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    },
    "status": {
      "active": true,
      "active$meta": {
        "confidence": "high",
        "note": "Mapped from article_status=\"active\"",
        "source": "parsed",
        "updated": "2026-05-22T23:54:08.922Z",
        "version": "smpte-journal-issue-xml@v1"
      }
    },
    "volume": "123",
    "volume$meta": {
      "confidence": "high",
      "note": "Parsed from journal_metadata XML (_source/SMPTE/APTARA/DL Project Files/10012015 BACKFILE JOURNAL REVISED/smptej_123_1/MIJR15Vol123No1.xml)",
      "source": "parsed",
      "updated": "2026-05-22T23:54:08.922Z",
      "version": "smpte-journal-issue-xml@v1"
    }
  }
}