Extended Data Fig. 6. Cross-subject encoding model and word rate model performance.

For each subject, encoding models and word rate models were trained on anatomically aligned brain responses from 5 sets of other subjects (indicated by markers). The models were evaluated on within-subject single-trial responses to the perceived speech test story. (a) Cross-subject encoding models performed significantly worse than within-subject encoding models (* indicates $q\left(\text{FDR}\right)<0.05$, two-sided $t$-test). (b) Cross-subject word rate models performed significantly worse than within-subject word rate models (* indicates $q\left(\text{FDR}\right)<0.05$, two-sided $t$-test).