@article{al-sabbagh-2026-ramsa,
    title = "Ramsa: A Large Sociolinguistically Rich Emirati {A}rabic Speech Corpus for {ASR} and {TTS}",
    author = "Al-Sabbagh, Rania",
    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.250/",
    pages = "3184--3198",
    abstract = "Ramsa is a developing 41-hour speech corpus of Emirati Arabic designed to support sociolinguistic research and low-resource language technologies. It contains recordings from structured interviews with native speakers and episodes from national television shows. The corpus features 157 speakers (59 female, 98 male), spans subdialects such as Urban, Bedouin, and Mountain/Shihhi, and covers topics such as cultural heritage, agriculture and sustainability, daily life, professional trajectories, and architecture. It consists of 91 monologic and 79 dialogic recordings, varying in length and recording conditions. A 10{\%} subset was used to evaluate commercial and open-source models for automatic speech recognition (ASR) and text-to-speech (TTS) in a zero-shot setting to establish initial baselines. Whisper-large-v3-turbo achieved the best ASR performance, with average word and character error rates of 0.268 and 0.144, respectively. MMS-TTS-Ara reported the best mean word and character rates of 0.285 and 0.081, respectively, for TTS. These baselines are competitive but leave substantial room for improvement. The paper highlights the challenges encountered and provides directions for future work."
}