Neural Network-Based Spatial Filtration of Sound
The majority of hearing impaired people have serious difficulty in understanding speech under "cocktail-party" conditions. One approach to help such people is to provide spatial filtering features in hearing prostheses. For this purpose a non-linear filter based on neural networks was designed and engineered. Several tests were performed in order to check the developed system spatial filtering effectiveness in real-life situations.
Click to purchase paper or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!
This paper costs $20 for non-members, $5 for AES members and is free for E-Library subscribers.