{
  "$schema": "/api/schemas/documents.schema.json",
  "apiVersion": "1.1.0",
  "lastModified": "2026-10-15T10:03:40.283Z",
  "sourcePath": "src/main/data/docs",
  "docId": "10.5594-M002027",
  "document": {
    "abstract": "This research provides a comprehensive review of prevailing Automatic Speech Recognition (ASR) methods and their profound impact on media production. Central to this exploration is the pivotal role of the transformer model, showcasing its unique self-attention mechanism ideal for tasks demanding comprehension of temporal relationships. We conduct an in- depth comparison, evaluating leading ASR models like Multilingual Machine Speech (MMS) from Meta, Whisper from OpenAI, and Google's Universal Speech Model (USM). Their performance is gauged against commercial services from tech giants such as Microsoft Azure, Amazon Web Services, and Google Cloud Platform. The paper covers aspects of ASR systems like voice activity detection, language identification, multilanguage support and the metrics used to characterize the accuracy of the systems. The research also identifies important challenges, like the dearth of data for some languages and the intricacies associated with linguistic nuances. Further, we discuss the role of ASR in media production, ranging from generating time-based captions to revolutionizing editing methodologies. Through a detailed breakdown of the ASR process, from audio preprocessing to postprocessing, this study endeavors to merge academic insights with practical applications, empowering media producers to leverage the immense capabilities of contemporary ASR technologies.",
    "abstract$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "authors": [
      {
        "affiliation": "Avid Technology",
        "name": "Randy Fayan"
      },
      {
        "affiliation": "Avid Technology",
        "name": "Zahra Montajabi"
      },
      {
        "affiliation": "Avid Technology",
        "name": "Rob Gonsalves"
      }
    ],
    "authors$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "contentType": "orig-research",
    "contentType$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "copyright": {
      "holder": "Society of Motion Picture and Television Engineers, Inc.",
      "holder$meta": {
        "confidence": "high",
        "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
        "source": "parsed",
        "updated": "2026-10-07T17:09:33.718Z",
        "version": "smpte-idams-publication@v1"
      },
      "year": "2023",
      "year$meta": {
        "confidence": "high",
        "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
        "source": "parsed",
        "updated": "2026-10-07T17:09:33.718Z",
        "version": "smpte-idams-publication@v1"
      }
    },
    "copyright$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "docId": "10.5594-M002027",
    "docId$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "docLabel": "SMPTE Meetings and Conferences ( October 2023)",
    "docLabel$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "docTitle": "Enhancing Content Creation Workflows through Automatic Speech Recognition Techniques",
    "docTitle$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "docType": "Conference Paper",
    "docType$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "doi": "10.5594/M002027",
    "doi$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "href": "https://doi.org/10.5594/M002027",
    "href$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "isbn": {
      "print": "978-1-61482-964-5",
      "print$meta": {
        "confidence": "high",
        "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
        "source": "parsed",
        "updated": "2026-10-07T17:09:33.718Z",
        "version": "smpte-idams-publication@v1"
      }
    },
    "isbn$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "keywords": [
      "Artificial Intelligence",
      "Machine Learning",
      "Automatic Speech Recognition"
    ],
    "keywords$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "number": "10",
    "number$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "pages": "14–16",
    "pages$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "publicationDate": "2023-10-16",
    "publicationDate$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "publisher": "SMPTE",
    "publisher$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "publisherLocation": {
      "city": "White Plains, NY",
      "city$meta": {
        "confidence": "high",
        "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
        "source": "parsed",
        "updated": "2026-10-07T17:09:33.718Z",
        "version": "smpte-idams-publication@v1"
      },
      "country": "USA",
      "country$meta": {
        "confidence": "high",
        "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
        "source": "parsed",
        "updated": "2026-10-07T17:09:33.718Z",
        "version": "smpte-idams-publication@v1"
      }
    },
    "publisherLocation$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    },
    "references": {
      "bibliographic": [
        "orphan/10.5594-M002027/h:77afadfe",
        "orphan/10.5594-M002027/h:a72ebd94",
        "orphan/10.5594-M002027/h:35031d88",
        "orphan/10.5594-M002027/h:7acbac08",
        "orphan/10.5594-M002027/h:a7324046",
        "orphan/10.5594-M002027/h:d4f78153",
        "orphan/10.5594-M002027/h:f0fa7372",
        "orphan/10.5594-M002027/h:3fef3845",
        "orphan/10.5594-M002027/h:7fd9df92",
        "orphan/10.5594-M002027/h:a417a492",
        "orphan/10.5594-M002027/h:72ce6742",
        "orphan/10.5594-M002027/h:9eab772d",
        "orphan/10.5594-M002027/h:61a2a8db",
        "orphan/10.5594-M002027/h:0fa1cbce",
        "orphan/10.5594-M002027/h:2ba2d456",
        "CTA.708-ES.2023",
        "orphan/10.5594-M002027/h:976e3ace",
        "orphan/10.5594-M002027/h:0e58bccc",
        "orphan/10.5594-M002027/h:0c0b062f",
        "orphan/10.5594-M002027/h:781b3c89",
        "orphan/10.5594-M002027/h:4c5bbf10",
        "orphan/10.5594-M002027/h:ba5e1163",
        "orphan/10.5594-M002027/h:26372b59",
        "orphan/10.5594-M002027/h:8de3fe75",
        "orphan/10.5594-M002027/h:e92c2b26"
      ],
      "bibliographic$meta": {
        "confidence": "medium",
        "flag": "PDF reference count (25) differs from Crossref (0); check the parse against the PDF",
        "note": "References parsed from the published PDF (Conference Repository/Conference Papers/2023/10372504/10372505/10372580.pdf). SMPTE's library delivery has no reference file or full text for this paper (src/main/reports/smpte-upstream/referenceFilesTruthTable.md). Cross-check: Crossref lists 0 reference(s) for this DOI; 25 parsed from the PDF.",
        "originalValue": [],
        "overridden": true,
        "reviewRequired": true,
        "source": "parsed",
        "updated": "2026-10-07T20:50:36.438Z",
        "version": "extractDocs.js@commit:d25f34130540"
      }
    },
    "resolvedHref": "https://journal.smpte.org/conferences/SMPTE%202023%20Media%20Technology%20Summit/35/",
    "resolvedHref$meta": {
      "confidence": "high",
      "note": "Backfilled from url.validate report #resolvedHref",
      "originalValue": null,
      "source": "resolved",
      "updated": "2026-10-15T10:03:40.283Z"
    },
    "status": {
      "active": true,
      "active$meta": {
        "confidence": "high",
        "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
        "source": "parsed",
        "updated": "2026-10-07T17:09:33.718Z",
        "version": "smpte-idams-publication@v1"
      }
    },
    "volume": "2023",
    "volume$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE IDAMS <publication> (_source/SMPTE/Conference Repository/Conference Papers/2023/10372504/10372505/10372580.xml) via idamsIngest.js",
      "source": "parsed",
      "updated": "2026-10-07T17:09:33.718Z",
      "version": "smpte-idams-publication@v1"
    }
  }
}