Model Releases
Phoneme- vs. Character-Level Targets and Selective State-Space Models for Intracortical Brain-to-Text
arXiv:2607.26751v1 Announce Type: new Abstract: State-of-the-art intracortical brain-to-text systems pair a neural-sequence phone decoder with an external language model. Two design axes remain undere
arXiv:2607.26751v1 Announce Type: new Abstract: State-of-the-art intracortical brain-to-text systems pair a neural-sequence phone decoder with an external language model. Two design axes remain underexplored: whether selective state-space models (Mamba) improve on recurrent decoders, and how the output target (phonetic vs. character) interacts with that choice. On the public Brain-to-Text '25 benchmark, we study a controlled 2x2 grid (GRU vs. hybrid Mamba decoder; phonetic vs. character targets) trained with a CTC objective under one reproducible protocol. The recurrent baseline remains strongest: the best phonetic GRU reaches 12.62% PER and 21.19% WER, while the best textual GRU after LM rescoring reaches 13.39% CER and 26.28% WER. The Mamba hybrid is competitive but does not surpass it. Ablations isolate architectural contributions, and error analysis shows representation-dependent failures: articulatory-like phoneme confusions vs. lexical and word-boundary errors.
Related
- The Capacity of Thought: Benchmarking Llama 3.2 in Semantic fMRI Neural Language Decoding and Improving the Huth Encoding-Model Baseline
- Harmonic: Hierarchical State Space Models for Efficient Long-Context Language Modeling
- TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior
Source: arXiv cs.CL | 2026-07-30