Cortical and Subcortical Articulatory Representations of Two Languages Revealed by Speech Decoding Based on sEEG

Numerous studies have suggested that the sensorimotor area may play a role in speech decoding due to its involvement in controlling the movement of vocal organs and its close link to speech. However, due to limitations in surface neural recording methods such as EEG and ECoG, it remains uncertain whether deep brain regions are capable of speech decoding. In this study, we utilized two sets of stereo electroencephalography (sEEG) data to investigate how speech is represented in both cortical and subcortical areas when people speak two different languages. The first sEEG dataset involved 10 subjects speaking Dutch, while the second dataset involved 5 subjects speaking Chinese. Consistent with previous studies, specific brain gyrus locations were closely linked to speech. We also discovered that high decoding performance could be achieved in many deep regions when subjects speak two languages. Furthermore, despite the two languages sharing similar articulation representation, they exhibited differences in neural representation, particularly in terms of high and low-frequency differences of audio. The differences of Chinese speakers were greater than those of Dutch speakers. We anticipate that future studies analyzing more data will uncover more precise articulatory representations of cortical and subcortical structures.