@inproceedings{podziubanchuk-etal-2026-simultaneous,
    title = "Simultaneous Speech-to-Text Translation Web Application for {E}stonian",
    author = {Podziubanchuk, Bohdan  and
      Olev, Aivo  and
      Kong, Jiaming  and
      Alum{\"a}e, Tanel},
    editor = "Croce, Danilo  and
      Leidner, Jochen  and
      Moosavi, Nafise Sadat",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = mar,
    year = "2026",
    address = "Rabat, Marocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-demo.40/",
    pages = "575--582",
    ISBN = "979-8-89176-382-1",
    abstract = "This paper presents a new open-source web application for simultaneous speech-to-text translation. The system translates live Estonian speech into English, Russian, and Ukrainian text, and also supports English-to-Estonian translation. Our solution uses a cascaded architecture that combines streaming speech recognition with a recently proposed LLM-based simultaneous translation model. The LLM treats translation as a conversation, processing input in small five-word chunks. Our streaming speech recognition achieves a word error rate of 10.2{\%} and a BLEU score of 26.1 for Estonian-to-English, significantly outperforming existing streaming solutions. The application is designed for real-world use, featuring a latency of only 3 - 6 seconds. The application is available at https://est2eng.vercel.app."
}