Brain-Informed Speech Separation for Cochlear Implants
Abstract
We propose a brain-informed speech separation method for cochlear implants (CIs) that uses electroencephalography (EEG)-derived attention cues to guide enhancement toward the attended speaker. An attention-guided network fuses audio mixtures with EEG features through a lightweight fusion layer, producing attended-source electrodograms for CI stimulation while resolving the label-permutation ambiguity of audio-only separators. Robustness to degraded attention cues is improved with a mixed curriculum that varies cue quality during training, yielding stable gains even when EEG-speech correlation is moderate. In multi-talker conditions, the model achieves higher signal-to-interference ratio improvements than an audio-only electrodogram baseline while remaining slightly smaller (167k vs. 171k parameters). With 2 ms algorithmic latency and comparable cost, the approach highlights the promise of coupling auditory and neural cues for cognitively adaptive CI processing.
Cite
@article{arxiv.2601.22260,
title = {Brain-Informed Speech Separation for Cochlear Implants},
author = {Tom Gajecki and Jonas Althoff and Waldo Nogueira},
journal= {arXiv preprint arXiv:2601.22260},
year = {2026}
}