Metraipolis › archive › dc_ea59b35e687d

Cross-Subject Generalization in Decoding Perceived Speech from Non-Invasive Brain Recordings — arXiv:2608.22420

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.22420
License (as archived)
CC0-1.0
Archived
2026-10-18T07:44:50.824Z
SHA-256 of the archived text
3884831fc2dcc6c6e604e13e7bd6f9e99468599c9ca6ad5b59e7bc03609e9432
Stable URL of this page
https://metraipolis.com/documento/dc_ea59b35e687d

How to cite

Cross-Subject Generalization in Decoding Perceived Speech from Non-Invasive Brain Recordings — arXiv:2608.22420 — arXiv (en), https://arxiv.org/abs/2608.22420 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea59b35e687d (Metraipolis archive dc_ea59b35e687d, sha256 3884831fc2dcc6c6e604e13e7bd6f9e99468599c9ca6ad5b59e7bc03609e9432)
BibTeX
@misc{dcea59b35e687d,
  title = {Cross-Subject Generalization in Decoding Perceived Speech from Non-Invasive Brain Recordings — arXiv:2608.22420},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22420},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea59b35e687d; sha256 3884831fc2dcc6c6e604e13e7bd6f9e99468599c9ca6ad5b59e7bc03609e9432},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22420. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Decoding perceived speech from non-invasive brain recordings has garnered significant attention in recent years due to its wide range of potential applications. However, existing methods face considerable challenges in cross-subject decoding, primarily due to limited generalizability and the absence of explicit mechanisms for extracting subject-consistent information. These limitations result in high training costs and suboptimal decoding performance. To address these challenges, we propose an innovative Cross-Subject Perceived Speech Decoding (CPSD) framework, which comprises two training stages: source model pre-training and personal specialization. In the source model pre-training stage, contrastive learning is employed to capture shared representations across multiple source subjects. Subsequently, personal specialization initializes the model for the target subject by extracting consistent components from the source model and fine-tuning it using target subject data. Additionally, we introduce the Positional Encoding-based Spatial Attention (PESA) module, which remaps MEG/EEG data into a standardized reference space, thereby enhancing cross-subject consistency and facilitating model training. We evaluate the proposed CPSD framework on three perceived speech neural datasets encompassing different modalities and languages. The results demonstrate that our framework outperforms baseline methods by more than 6.8%, 15.4%, and 15.8% in Top-10 accuracy on the Armeni 2022, PKUEEG 2025, and Broderick 2018 datasets, respectively. Further analyses confirm the effectiveness, efficiency, and robustness of the proposed approach.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.22420 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T07:37:52.878Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).