This contribution is devoted to the noise suppression system for monoaural SPEAK-type cochlear implants. The system is based on the combination of the superdirective two-microphone array and the noise suppression post-processing, both implemented in the frequency domain. The relative insensitivity of the two-microphone superdirective system to the spectral magnitude differences in both channels enables the two-channel noise suppression post-processing. The new criterion originating from the SPEAK coding strategy is used for the evaluation of the whole system.
Cite as: Svoboda, M., Sovka, P., Pollák, P. (1999) Combined noise suppression system for monaural cochlear implants. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 2635-2638, doi: 10.21437/Eurospeech.1999-581
@inproceedings{svoboda99_eurospeech,
author={Milan Svoboda and Pavel Sovka and Petr Pollák},
title={{Combined noise suppression system for monaural cochlear implants}},
year=1999,
booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
pages={2635--2638},
doi={10.21437/Eurospeech.1999-581}
}