Head Orientation Estimation from Multiple Microphone Arrays
Rebecca C. Felsheim, Andreas Brendel, Patrick A. Naylor, Walter Kellermann · 2020
Knowledge of head orientation is important for various audio signal processing tasks involving human speakers, including speech enhancement and attention tracking. Most of the methods estimate the head orientation using video information which, however, is not always available. In this work, two known audio features for head orientation estimation are reviewed and three new features are proposed. Furthermore, all evaluated features have been combined in two different ways: with a linear combination and a small artificial neural network. The resulting algorithms are able to detect the head orientation in our experiments with high precision and show superior performance over state-of-the-art methods.