@inproceedings{bondarenko-etal-2025-pisets,
    title = "Pisets: A Robust Speech Recognition System for Lectures and Interviews",
    author = "Bondarenko, Ivan  and
      Grebenkin, Daniil  and
      Sedukhin, Oleg  and
      Klementev, Mikhail  and
      Roman, Derunets  and
      Budneva, Lyudmila",
    editor = "Chen, Weizhu  and
      Yang, Yi  and
      Kachuee, Mohammad  and
      Fu, Xue-Yong",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-industry.74/",
    pages = "988--997",
    ISBN = "979-8-89176-194-0",
    abstract = "This work presents a speech-to-text system ``Pisets'' for scientists and journalists which is based on a three-component architecture aimed at improving speech recognition accuracy while minimizing errors and hallucinations associated with the Whisper model. The architecture comprises primary recognition using Wav2Vec2, false positive filtering via the Audio Spectrogram Transformer (AST), and final speech recognition through Whisper. The implementation of curriculum learning methods and the utilization of diverse Russian-language speech corpora significantly enhanced the system{'}s effectiveness. Additionally, advanced uncertainty modeling techniques were introduced, contributing to further improvements in transcription quality. The proposed approaches ensure robust transcribing of long audio data across various acoustic conditions compared to WhisperX and the usual Whisper model. The source code of ``Pisets'' system is publicly available at GitHub: https://github.com/bond005/pisets."
}