Environment-adaptive speech enhancement for bilateral cochlear implants using a single processor

A computationally efficient speech enhancement pipeline in noisy environments based on a single-processor implementation is developed for utilization in bilateral cochlear implant systems. A two-channel joint objective function is defined and a closed form solution is obtained based on the weighted-Euclidean distortion measure. The computational efficiency and no need for synchronization aspects of this pipeline make it a suitable solution for real-time deployment. A speech quality measure is used to show its effectiveness in six different noisy environments as compared to a similar one-channel enhancement pipeline when using two separate processors or when using independent sequential processing.

► A single-processor enhancement approach has been introduced in this paper for deployment in bilateral cochlear implant systems.
► By performing the optimization of suppression and binaural reconstruction gain parameters in a data-driven manner, it has been shown that it can be tuned to different noise types with different characteristics.
► The PESQ quality assessment measure in six different commonly encountered noisy environments showed that the performance loss was statistically not significant compared to the independent processing of the left and right signals.
► The proposed pipeline is suitable for real-time deployment because of its computational and storage efficiency.