Decoding Continuous Character-based Language from Non-invasive Brain Recordings
This addresses the problem of enabling non-invasive brain-computer interfaces for language decoding, with potential applications in healthcare and neuroscience, representing a novel method for a known bottleneck.
The paper tackled the challenge of decoding continuous natural language from single-trial non-invasive fMRI brain recordings, achieving intelligible textual sequences that capture meaning both within and across subjects, with performance superior to existing decoders in cross-subject contexts.
Deciphering natural language from brain activity through non-invasive devices remains a formidable challenge. Previous non-invasive decoders either require multiple experiments with identical stimuli to pinpoint cortical regions and enhance signal-to-noise ratios in brain activity, or they are limited to discerning basic linguistic elements such as letters and words. We propose a novel approach to decoding continuous language from single-trial non-invasive fMRI recordings, in which a three-dimensional convolutional network augmented with information bottleneck is developed to automatically identify responsive voxels to stimuli, and a character-based decoder is designed for the semantic reconstruction of continuous language characterized by inherent character structures. The resulting decoder can produce intelligible textual sequences that faithfully capture the meaning of perceived speech both within and across subjects, while existing decoders exhibit significantly inferior performance in cross-subject contexts. The ability to decode continuous language from single trials across subjects demonstrates the promising applications of non-invasive language brain-computer interfaces in both healthcare and neuroscience.