Fig. 3: Word-level predictions. | Nature Machine Intelligence

Fig. 3: Word-level predictions.

From: Decoding speech perception from non-invasive brain recordings

Fig. 3: Word-level predictions.The alternative text for this image may have been generated using AI.

Word-level predictions for five representative participants (between the 20% (top) and the 80% percentiles (bottom) of the cohort) of the Gwilliams dataset33 while they listened to the sentence ‘Thank you for coming, Ed’. Blue words correspond to the correct word and black words correspond to negative candidates. Text size is proportional to the log-probability output by our model.

Back to article page