{
  "$schema": "/api/schemas/documents.schema.json",
  "apiVersion": "1.0.0",
  "generatedAt": "2026-07-14T19:46:21.019Z",
  "sourcePath": "src/main/data/docs",
  "docId": "10.5594-JMI.2024-IPYX8877__2024-SMPTEMIJAPRIL2024_18-18",
  "document": {
    "abbrevTitle": "SMPTE Motion Imaging Jour.",
    "abbrevTitle$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "abstract": "This research offers an in-depth review of current Automatic Speech Recognition (ASR) methods and their significant impact on media production, with a focus on the transformer model's self-attention mechanism for understanding sequential relationships. It compares accuracy and performance of top ASR models like Meta's Multilingual Machine Speech, OpenAI's Whisper, and Google's Universal Speech Model along with services from Microsoft Azure, Amazon Web Services, and Google Cloud Platform. The study examines key ASR aspects, including voice activity detection, language identification, and multilanguage support, and evaluates their accuracy metrics. Challenges such as limited data for certain languages and complexities in linguistic nuances are highlighted. Additionally, the paper discusses ASR's role in media production, from creating time-based captions to transforming editing techniques. By analyzing the ASR process from audio preprocessing to post-processing, the research bridges academic and practical perspectives, enabling media producers to utilize advanced ASR technologies effectively.",
    "abstract$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "authors": [
      {
        "name": "Randy Fayan"
      },
      {
        "name": "Zahra Montajabi"
      },
      {
        "name": "Rob Gonsalves"
      }
    ],
    "authors$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "contentType": "orig-research",
    "contentType$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "copyright": {
      "holder": "SMPTE",
      "holder$meta": {
        "confidence": "medium",
        "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
        "source": "parsed",
        "updated": "2026-07-10T20:01:10.986Z"
      },
      "year": "2024",
      "year$meta": {
        "confidence": "medium",
        "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
        "source": "parsed",
        "updated": "2026-07-10T20:01:10.986Z"
      }
    },
    "copyright$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "docId": "10.5594-JMI.2024-IPYX8877__2024-SMPTEMIJAPRIL2024_18-18",
    "docId$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "docLabel": "MIJ 2024, Volume 133, Number 2 (pp. 48 to 57)",
    "docLabel$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "docTitle": "Automatic Speech Recognition with Machine Learning: Techniques and Evaluation of Current Tools",
    "docTitle$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "docType": "Journal Article",
    "docType$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "doi": "10.5594/JMI.2024/IPYX8877",
    "doi$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "doiCollision": "10.5594/JMI.2024/IPYX8877",
    "doiCollision$meta": {
      "confidence": "high",
      "note": "SMPTE assigned this DOI to >1 paper; docId disambiguated pending upstream fix.",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "href": "https://doi.org/10.5594/JMI.2024/IPYX8877",
    "href$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "issn": {
      "electronic": "2160-2492",
      "electronic$meta": {
        "confidence": "medium",
        "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
        "source": "parsed",
        "updated": "2026-07-10T20:01:10.986Z"
      },
      "print": "1545-0279",
      "print$meta": {
        "confidence": "medium",
        "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
        "source": "parsed",
        "updated": "2026-07-10T20:01:10.986Z"
      }
    },
    "issn$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "journalAcronym": "MIJ",
    "journalAcronym$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "journalTitle": "SMPTE Motion Imaging Journal",
    "journalTitle$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "keywords": [
      "Artificial Intelligence",
      "Machine Learning",
      "Automatic Speech Recognition"
    ],
    "keywords$meta": {
      "confidence": "high",
      "note": "Keywords conformed via keywordConformIngest.js — vocab/fold mapping (keywordVocabDecisions.json) + casing normalize; long-tail retained pending later triage.",
      "source": "resolved",
      "updated": "2026-07-10T22:58:01.636Z"
    },
    "number": "2",
    "number$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "pages": "48–57",
    "pages$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "publicationDate": "2024-04-01",
    "publicationDate$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "publisher": "SMPTE",
    "publisher$meta": {
      "confidence": "medium",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    },
    "status": {
      "active": true,
      "active$meta": {
        "confidence": "medium",
        "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
        "source": "parsed",
        "updated": "2026-07-10T20:01:10.986Z"
      }
    },
    "volume": "133",
    "volume$meta": {
      "confidence": "high",
      "note": "Ingested from SMPTE canonical content_batch via ingestNlmCanonicalDocs.js",
      "source": "parsed",
      "updated": "2026-07-10T20:01:10.986Z"
    }
  }
}