Brain-Informed Speech Separation for Cochlear Implants

TL;DR

This paper introduces a novel brain-informed speech separation method for cochlear implants that leverages EEG-derived attention cues to improve speech clarity and robustness in multi-talker environments.

Contribution

It presents a new EEG-guided neural network that enhances cochlear implant stimulation, addressing label ambiguity and robustness to cue degradation.

Findings

Achieves higher signal-to-interference ratio than audio-only methods.

Maintains stable performance with moderate EEG-speech correlation.

Operates with low latency and similar computational cost.

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.