@inproceedings{aparin-etal-2026-audiosae,
    title = "{A}udio{SAE}: Towards Understanding of Audio-Processing Models with Sparse {A}uto{E}ncoders",
    author = "Aparin, Georgii  and
      Sadekova, Tasnima  and
      Rukhovich, Alexey  and
      Yermekova, Assel  and
      Kushnareva, Laida  and
      Popov, Vadim  and
      Kuznetsov, Kristian  and
      Piontkovskaya, Irina",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.149/",
    pages = "3221--3254",
    ISBN = "979-8-89176-380-7",
    abstract = "Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whisper and HuBERT, provide an extensive evaluation of their stability, interpretability, and show their practical utility. Over 50{\%} of the features remain consistent across random seeds, and reconstruction quality is preserved. SAE features capture general acoustic and semantic information as well as specific events, including environmental noises and paralinguistic sounds (e.g. laughter, whispering) and disentangle them effectively, requiring removal of only 19-27{\%} of features to erase a concept. Feature steering reduces Whisper{'}s false speech detections by 70{\%} with negligible WER increase, demonstrating real-world applicability. Finally, we find SAE features correlated with human EEG activity during speech perception, indicating alignment with human neural processing. The code and checkpoints are available at https://github.com/audiosae/audiosae{\_}demo."
}