| Paper ID | AUD-11.3 |
| Paper Title |
COMPUTATIONALLY EFFICIENT DNN-BASED APPROXIMATION OF AN AUDITORY MODEL FOR APPLICATIONS IN SPEECH PROCESSING |
| Authors |
Anil Nagathil, Florian Göbel, Alexandru Nelus, Ruhr-Universität Bochum, Germany; Ian C. Bruce, McMaster University, Canada |
| Session | AUD-11: Auditory Modeling and Hearing Instruments |
| Location | Gather.Town |
| Session Time: | Wednesday, 09 June, 14:00 - 14:45 |
| Presentation Time: | Wednesday, 09 June, 14:00 - 14:45 |
| Presentation |
Poster
|
| Topic |
Audio and Acoustic Signal Processing: [AUD-AMHI] Auditory Modeling and Hearing Instruments |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Computational models of the auditory periphery are important tools for understanding mechanisms of normal and impaired hearing and for developing advanced speech and audio processing algorithms. However, the simulation of accurate neural representations entails a high computational effort. This prevents the use of auditory models in applications with real-time requirements and the design of speech enhancement algorithms based on efficient bio-inspired optimization criteria. Hence, in this work we propose and evaluate DNN-based approximations of a state-of-the-art auditory model. The DNN models yield accurate neurogram predictions for previously unseen speech signals with processing times shorter than signal duration, thus indicating their potential to be applied in real-time. |
