Recent studies have shown that Deep neural Networks (DNNs) are capable of detecting sound source azimuth direction in adverse environments to a high level of accuracy. This paper expands on these findings by presenting research that explores the use of DNNs in determining sound source elevation. A simple machine-hearing system is presented that is capable of predicting source elevation to a relatively high degree of accuracy in both anechoic and reverberant environments. Speech signals spatialized across the front hemifield of the head are used to train a feedforward neural network. The effectiveness of Gammatone Filter Energies (GFEs) and the Cross-Correlation Function (CCF) in estimating elevation is investigated as well as binaural cues such as Interaural Time Difference (ITD) and Interaural Level Difference (ILD). Using a combination of these cues, it was found that elevation to within 10 degrees could be predicted with an accuracy upward of 80%.
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.