To improve the computation of sound impulse response for the virtual audio environment technique, a neural network approach has been developed to forecast the sound impulse response from the computed data obtained with simulation software. A three-layered neural network was used. Methodology of the approach and optimum architecture of the network are described. Application examples are presented and compared with practical response.
Click to purchase paper as a non-member 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 $33 for non-members and is free for AES members and E-Library subscribers.