@inproceedings{salesky-etal-2019-exploring,
    title = "Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation",
    author = "Salesky, Elizabeth  and
      Sperber, Matthias  and
      Black, Alan W",
    editor = "Korhonen, Anna  and
      Traum, David  and
      M{\`a}rquez, Llu{\'i}s",
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/P19-1179/",
    doi = "10.18653/v1/P19-1179",
    pages = "1835--1841",
    abstract = "Previous work on end-to-end translation from speech has primarily used frame-level features as speech representations, which creates longer, sparser sequences than text. We show that a naive method to create compressed phoneme-like speech representations is far more effective and efficient for translation than traditional frame-level speech features. Specifically, we generate phoneme labels for speech frames and average consecutive frames with the same label to create shorter, higher-level source sequences for translation. We see improvements of up to 5 BLEU on both our high and low resource language pairs, with a reduction in training time of 60{\%}. Our improvements hold across multiple data sizes and two language pairs."
}