| Paper ID | SS-10.4 |
| Paper Title |
A NOISE-ROBUST SIGNAL PROCESSING STRATEGY FOR COCHLEAR IMPLANTS USING NEURAL NETWORKS |
| Authors |
Nengheng Zheng, Shenzhen University, China; Yupeng Shi, Tencent Media Lab, China; Yuyong Kang, Shenzhen University, China; Qinglin Meng, South China University of Technology, China |
| Session | SS-10: Computer Audition for Healthcare (CA4H) |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 13:00 - 13:45 |
| Presentation Time: | Thursday, 10 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Special Sessions: Computer Audition for Healthcare (CA4H) |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Signal processing strategies in most clinical cochlear implants (CIs) extract and transmit speech envelopes to stimulate the auditory neurons. The incomplete representation of the rich fine structures in speech has significantly degraded the CI recipients’ ability in high-level perception, including their speech under-standing in noise. This paper presents a noise-robust signal pro-cessing strategy to deal with this problem. Neural networks (NN) are built and trained to simulate the advanced combination en-coder (ACE, a strategy for CI products of Cochlear Corporation). The NN-based ACE (namely, NNACE) is trained with a sophis-ticatedly designed loss function to output envelope-like signals that 1) is compatible with ACE-based CI system and can serve as the modulator to generate the electric stimuli, 2) is more noise-robust, and 3) might bear a certain degree of the temporal fine structures of speech. Subjective and objective evaluations with vocoder simulated speech show that NNACE outperforms the other methods and further actual CI experiments are warranted. |
