@inproceedings{gajewska-etal-2025-voice,
    title = "Voice synthesis in {P}olish and {E}nglish - analyzing prediction differences in speaker verification systems",
    author = "Gajewska, Joanna  and
      Martinek, Alicja  and
      O{\l}owski, Micha{\l} J.  and
      Bartuzi-Trokielewicz, Ewelina",
    editor = "Rambow, Owen  and
      Wanner, Leo  and
      Apidianaki, Marianna  and
      Al-Khalifa, Hend  and
      Eugenio, Barbara Di  and
      Schockaert, Steven",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2025.coling-main.643/",
    pages = "9618--9629",
    abstract = "Deep learning has significantly enhanced voice synthesis, yielding realistic audio capable of mimicking individual voices. This progress, however, raises security concerns due to the potential misuse of audio deepfakes. Our research examines the effects of deepfakes on speaker recognition systems across English and Polish corpora, assessing both Text-to-Speech and Voice Conversion methods. We focus on the biometric similarity`s role in the effectiveness of impersonations and find that synthetic voices can maintain personal traits, posing risks of unauthorized access. The study`s key contributions include analyzing voice synthesis across languages, evaluating biometric resemblance in voice conversion, and contrasting Text-to-Speech and Voice Conversion paradigms. These insights emphasize the need for improved biometric security against audio deepfake threats."
}