Relating the Neural Representations of Vocalized, Mimed, and Imagined Speech
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911469833027584 |
|---|---|
| author | Maghsoudi, Maryam Chillale, Rupesh Shamma, Shihab A. |
| author_facet | Maghsoudi, Maryam Chillale, Rupesh Shamma, Shihab A. |
| contents | We investigated the relationship among neural representations of vocalized, mimed, and imagined speech recorded using publicly available stereotactic EEG recordings. Most prior studies have focused on decoding speech responses within each condition separately. Here, instead, we explore how responses across conditions relate by training linear spectrogram reconstruction models for each condition and evaluate their generalization across conditions. We demonstrate that linear decoders trained on one condition generally transfer successfully to others, implying shared speech representations. This commonality was assessed with stimulus-level discriminability by performing a rank-based analysis demonstrating preservation of stimulus-specific structure in both within- and across-conditions. Finally, we compared linear reconstructions to those from a nonlinear neural network. While both exhibited cross-condition transfer, linear models achieve superior stimulus-level discriminability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22597 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Relating the Neural Representations of Vocalized, Mimed, and Imagined Speech Maghsoudi, Maryam Chillale, Rupesh Shamma, Shihab A. Sound Audio and Speech Processing Signal Processing We investigated the relationship among neural representations of vocalized, mimed, and imagined speech recorded using publicly available stereotactic EEG recordings. Most prior studies have focused on decoding speech responses within each condition separately. Here, instead, we explore how responses across conditions relate by training linear spectrogram reconstruction models for each condition and evaluate their generalization across conditions. We demonstrate that linear decoders trained on one condition generally transfer successfully to others, implying shared speech representations. This commonality was assessed with stimulus-level discriminability by performing a rank-based analysis demonstrating preservation of stimulus-specific structure in both within- and across-conditions. Finally, we compared linear reconstructions to those from a nonlinear neural network. While both exhibited cross-condition transfer, linear models achieve superior stimulus-level discriminability. |
| title | Relating the Neural Representations of Vocalized, Mimed, and Imagined Speech |
| topic | Sound Audio and Speech Processing Signal Processing |
| url | https://arxiv.org/abs/2602.22597 |