@inproceedings{moslem-2024-leveraging,
    title = "Leveraging Synthetic Audio Data for End-to-End Low-Resource Speech Translation",
    author = "Moslem, Yasmin",
    editor = "Salesky, Elizabeth  and
      Federico, Marcello  and
      Carpuat, Marine",
    booktitle = "Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand (in-person and online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.iwslt-1.31/",
    doi = "10.18653/v1/2024.iwslt-1.31",
    pages = "265--273",
    abstract = "This paper describes our system submission to the International Conference on Spoken Language Translation (IWSLT 2024) for Irish-to-English speech translation. We built end-to-end systems based on Whisper, and employed a number of data augmentation techniques, such as speech back-translation and noise augmentation. We investigate the effect of using synthetic audio data and discuss several methods for enriching signal diversity."
}