LightBeam: An Accurate and Memory-Efficient CTC Decoder for Speech Neuroprostheses
About
A promising pathway for restoring communication in patients with dysarthria and anarthria is speech neuroprostheses, which directly decode speech from cortical neural activity. Two benchmarks, Brain-to-Text '24 and '25, released intracranial recordings from patients with dysarthria along with a baseline algorithm trained with Connectionist Temporal Classification (CTC). Despite significant innovation on these benchmarks, all leading published prior work relies on a WFST-based CTC decoder that requires ${\sim}$320 GB of RAM. These memory requirements limit accessibility for both patients and researchers. Here, we propose LightBeam, a non-WFST based CTC decoder that requires only ${\sim}$10 GB of RAM and achieves state-of-the-art performance on both benchmarks. LightBeam achieves this by integrating an LLM into the beam-search process via delayed fusion, obviating the prior need for using a large N-gram LM. LightBeam is implemented in Python and is open-source.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Brain-to-Text Decoding | B2T '24 (test) | WER9.37 | 3 | |
| Brain-to-Text Decoding | B2T '25 (test) | Public WER5.77 | 3 |