MEG-to-MEG Transfer Learning and Cross-Task Speech/Silence Detection with Limited Data
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911459450028032 |
|---|---|
| author | de Zuazo, Xabier Verbeni, Vincenzo Navas, Eva Saratxaga, Ibon Bourguignon, Mathieu Molinaro, Nicola |
| author_facet | de Zuazo, Xabier Verbeni, Vincenzo Navas, Eva Saratxaga, Ibon Bourguignon, Mathieu Molinaro, Nicola |
| contents | Data-efficient neural decoding is a central challenge for speech brain-computer interfaces. We present the first demonstration of transfer learning and cross-task decoding for MEG-based speech models spanning perception and production. We pre-train a Conformer-based model on 50 hours of single-subject listening data and fine-tune on just 5 minutes per subject across 18 participants. Transfer learning yields consistent improvements, with in-task accuracy gains of 1-4% and larger cross-task gains of up to 5-6%. Not only does pre-training improve performance within each task, but it also enables reliable cross-task decoding between perception and production. Critically, models trained on speech production decode passive listening above chance, confirming that learned representations reflect shared neural processes rather than task-specific motor activity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18253 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MEG-to-MEG Transfer Learning and Cross-Task Speech/Silence Detection with Limited Data de Zuazo, Xabier Verbeni, Vincenzo Navas, Eva Saratxaga, Ibon Bourguignon, Mathieu Molinaro, Nicola Machine Learning 68T07 (Primary), 62H30 (Secondary) I.2.6; I.5.4 Data-efficient neural decoding is a central challenge for speech brain-computer interfaces. We present the first demonstration of transfer learning and cross-task decoding for MEG-based speech models spanning perception and production. We pre-train a Conformer-based model on 50 hours of single-subject listening data and fine-tune on just 5 minutes per subject across 18 participants. Transfer learning yields consistent improvements, with in-task accuracy gains of 1-4% and larger cross-task gains of up to 5-6%. Not only does pre-training improve performance within each task, but it also enables reliable cross-task decoding between perception and production. Critically, models trained on speech production decode passive listening above chance, confirming that learned representations reflect shared neural processes rather than task-specific motor activity. |
| title | MEG-to-MEG Transfer Learning and Cross-Task Speech/Silence Detection with Limited Data |
| topic | Machine Learning 68T07 (Primary), 62H30 (Secondary) I.2.6; I.5.4 |
| url | https://arxiv.org/abs/2602.18253 |