NeuroVox: Bilingual Brain-to-Speech Translation and Neural Activity Detection

Speech synthesis from brain signals offers a new way of speech communication, and enables innovative services and applications. With high temporal and spatial resolution, invasive braining sensing such as stereotactic electroencephalography (sEEG) becomes one of the promising solutions to decode complex brain dynamics.However, such data are hard to come by. We introduce a bilingual brain-to-speech synthesis (B2S2) dataset: the first publicly accessible sEEG recordings curated for bilingual brain-to-speech synthesis. Specifically, the B2S2 dataset comprises sEEG signals recorded while the speakers are reading Chinese words, English words, and Chinese digits. The B2S2 dataset is publicly available for research purposes.