@inproceedings{oberkircher-etal-2026-saar,
    title = {Saar-Voice: A Multi-Speaker Saarbr{\"u}cken Dialect Speech Corpus},
    author = {Oberkircher, Lena Sophie  and
      Alabi, Jesujoba  and
      Klakow, Dietrich  and
      Trouvain, J{\"u}rgen},
    editor = "Anastasopoulos, Antonis  and
      Markantonatou, Stella  and
      Ralli, Angela  and
      Zampieri, Marcos  and
      Bompolas, Stavros  and
      Stamou, Vivian",
    booktitle = "Proceedings of the First Workshop on Dialects in {NLP} {---} A Resource Perspective",
    month = may,
    year = "2026",
    address = "Palma de Mallorca",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.dialres-1.2/",
    doi = "10.63317/2xvbjjktadtu",
    pages = "12--23",
    abstract = {Natural language processing (NLP) and speech technologies have made significant progress in recent years; however, they remain largely focused on standardized language varieties. Dialects, despite their cultural significance and widespread use, are underrepresented in linguistic resources and computational models, resulting in performance disparities. To address this gap, we introduce Saar-Voice, a six-hour speech corpus for the Saarbr{\"u}cken dialect of German. The dataset was created by first collecting text through digitized books and locally sourced materials. A subset of this text was recorded by nine speakers, and we conducted analyses on both the textual and speech components to assess the dataset{'}s characteristics and quality. We discuss methodological challenges related to orthographic and speaker variation, and explore grapheme-to-phoneme (G2P) conversion. The resulting corpus provides aligned textual and audio representations. This serves as a foundation for future research on dialect-aware TTS, which is proposed in the form of zero-shot and fine-tuned model adaptation in low-resource scenarios.}
}