Deep neural network-based speech enhancement for cochlear implants

Abstract

Noisy conditions make understanding speech with a cochlear implant (CI) difficult. Speech enhancement (SE) algorithms based on signal statistics can be beneficial in stationary noise, but rarely provide benefit in modulated multi-talker babble. Current approaches using deep neural networks (DNNs) rely on a data driven approach for training and promise improvements in a wide variety of noisy conditions. In this study a DNN-based SE algorithm was evaluated in CI listeners. The network was trained on a large database of publicly available recordings. A double-blinded acute evaluation was conducted with 10 adult CI users by assessing intelligibility and quality of speech embedded in a range of different noise types. The DNN-based SE algorithm provided significant benefits in speech intelligibility and sound quality in all noise types that were evaluated. Speech reception thresholds, the SNR required to understand 50% of the speech material, improved by 1.8 to 3.5 dB depending on noise type. Benefits varied with the SNR of the input signal and the mixing ratio parameter that was used to combine the original and de-noised signals. The results demonstrate that DNN-based SE can provide benefits in natural, modulated noise conditions, which is critical to CI users in their day-to-day environment.