@inproceedings{iranmanesh-etal-2026-segmentation,
    title = "Segmentation Strategy Matters: Benchmarking Whisper on {P}ersian {Y}ou{T}ube Content",
    author = "Iranmanesh, Reihaneh  and
      Ziaei, Rojin  and
      Garman, Joe",
    editor = "Merchant, Rayyan  and
      Megerdoomian, Karine",
    booktitle = "The Proceedings of the First Workshop on {NLP} and {LLM}s for the {I}ranian Language Family",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.silkroadnlp-1.13/",
    pages = "121--130",
    ISBN = "979-8-89176-371-5",
    abstract = "Automatic Speech Recognition (ASR) transcription accuracy remains highly sensitive to audio segmentation strategies, yet most benchmarks assume oracle timestamps unavailable in deployment. We systematically evaluate how audio segmentation affects Whisper{'}s performance on 10 hours of Persian YouTube content, comparing transcript-aligned (oracle) versus silence-based (realistic) approaches across contrasting acoustic conditions. Results reveal striking content-type dependency: podcast content benefits from timestamp segmentation (33{\%} lower mean WER), while entertainment content favors silence-based segmentation (8{\%} lower mean WER). This finding demonstrates that optimal segmentation must be content-aware, with silence detection better capturing natural boundaries in acoustically heterogeneous media while avoiding mid-utterance splits. We publicly release our evaluation framework, 10 hours of audio with gold transcripts, and segmentation results here: https://github.com/ri164-bolleit/persian-youtube-whisper-benchmark"
}