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. Motivated by neuroscientific evidence that high-level semantic representations are distributed across cortical regions and evolve over slower temporal scales, we hypothesize that semantic content may provide a more suitable target for non-invasive decoding than low-level acoustic or lexical features. We introduce Brain2Semantics2Text, a method that reconstructs text through an intermediate semantic embedding s
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 49%What if context compression is a diffusion noise function? Proposal + honest results from untrained-model experiments [R] →
- FuzzySimilar title/name (fuzzy) · 87%huggingface/speech-to-speech →
“Fuzzy title match (0.94): “The Semantic Bottleneck: Leveraging Semantic Representations” ≈ “huggingface/speech-to-speech””
- FuzzySimilar title/name (fuzzy) · 59%microsoft/semantic-kernel →
“Fuzzy title match (0.73): “The Semantic Bottleneck: Leveraging Semantic Representations” ≈ “microsoft/semantic-kernel””
- LinkedLinked via arxiv author · 85%Gilad D. Landau →
“The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding”
- LinkedLinked via arxiv author · 85%Dulhan Jayalath →
“The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding”
- LinkedLinked via arxiv author · 85%Oiwi Parker Jones →
“The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding”