Abstract Objective : Brain-to-text systems have recently achieved impressive performance when trained on single-participant data, 
but remain limited by uninvestigated cross-subject generalization. 

 Approach: We present the first neural-to-phoneme decoder trained jointly on the two largest intracortical speech datasets 
(Willett et al. 2023; Card et al. 2024), 
introducing day- and dataset-specific affine transforms to align neural activity into a shared space. 
Additionally, a hierarchical GRU decoder with intermediate CTC supervision and feedback connections is designed to address
the conditional-independence assumption of standard CTC loss. 

 Main Results: Our model matches or outperforms within-subject baselines while being trained across participants, 
and adapts to unseen subjects using only a linear transform or brief fine-tuning. 
On an independent inner-speech dataset (Kunz et al. 2025), 
our approach shows some initial evidence of generalization, by training only subject-, day-specific transforms. 

 Significance: These results demonstrate the feasibility of cross-subject pretraining as a promising direction toward more scalable speech BCIs.