The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding

Non-invasive speech decoding remains constrained by the low signal-to-noise ratio of neural recordings, which makes fine-grained reconstruction of phonemes or individual words difficult, according to research motivated by neuroscientific evidence that high-level semantic representations are distributed across the cortex. The work proposes leveraging semantic representations as an alternative to phoneme- or word-level reconstruction for non-invasive speech decoding.

Non-invasive speech decoding remains constrained by the low signal-to-noise ratio of neural recordings, which makes fine-grained reconstruction of phonemes or individual words difficult. Motivated by neuroscientific evidence that high-level semantic representations are distributed across cortical re