Metraipolis › archive › dc_b5ea2e5f85b7

Contrastive Learning with Variational Regularization for Multi-Session EEG-to-Speech Decoding — arXiv:2608.16360

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16360
License (as archived)
CC0-1.0
Archived
2026-10-19T02:16:12.183Z
SHA-256 of the archived text
098b47bbce1a82e986af04964d90ba4e03eb43d510f8237422785cbe42b70a48
Stable URL of this page
https://metraipolis.com/documento/dc_b5ea2e5f85b7

How to cite

Contrastive Learning with Variational Regularization for Multi-Session EEG-to-Speech Decoding — arXiv:2608.16360 — arXiv (en), https://arxiv.org/abs/2608.16360 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b5ea2e5f85b7 (Metraipolis archive dc_b5ea2e5f85b7, sha256 098b47bbce1a82e986af04964d90ba4e03eb43d510f8237422785cbe42b70a48)
BibTeX
@misc{dcb5ea2e5f85b7,
  title = {Contrastive Learning with Variational Regularization for Multi-Session EEG-to-Speech Decoding — arXiv:2608.16360},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16360},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b5ea2e5f85b7; sha256 098b47bbce1a82e986af04964d90ba4e03eb43d510f8237422785cbe42b70a48},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16360. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reconstructing heard speech from non-invasive electroencephalography (EEG) is challenging due to a low signal-to-noise ratio (SNR) and inter-session variability. While trial averaging improves the SNR, it is difficult to apply to continuous speech. We instead use repeated EEG responses to the same stimulus across different sessions as positive pairs for contrastive learning, and introduce variational regularization that, combined with this contrastive objective, keeps the encoder representation space broad. Experiments on a Japanese EEG dataset show that combining the session-invariant strategy with variational regularization improves the character error rate (CER) while maintaining mel-spectrogram reconstruction fidelity. Session probing confirms that the encoder representations achieve session-invariance.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-18 in eess.SP).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Sound (cs.SD); Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2608.16360 — 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 2026-10-19T01:25:14.346Z dalla pagina https://arxiv.org/catchup/eess.SP/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).