@article{draxler-etal-2026-semi,
    title = "A Semi-Automatic Workflow for Transcribing and Annotating Broadcast News",
    author = {Draxler, Christoph  and
      Grawunder, Sven  and
      Trouvain, J{\"u}rgen  and
      Kleber, Felicitas},
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.508/",
    pages = "6408--6417",
    abstract = "Audio data archived in radio broadcast stations represent a rich source for various research purposes from phonetic questions up to training and test data for speech modelling. We present an efficient semi-automatic workflow for pre-processing, transcribing and analysing large linguistic-phonetic audio corpora. As a pilot study, we process radio broadcast news from a German public radio station containing recordings from 1956 until 2017. The workflow consists of basic preprocessing, automatic speech recognition, manual word correction, automatic generation of pairs of audio chunks and transcripts, plus an automatic word-, syllable- and phoneme-level segmentation of these chunks. The workflow is organised using the Octra Backend management tool, manual validation and correction of transcripts and chunking are performed using the Octra editor, and the BAS web services perform the segmentation. In an example analysis we show with our specific radio corpus how to use it for comparative longitudinal structure analyses of broadcast news, and for text- and signal-based studies on changes of speech and articulation rate."
}