Abstract: Presented herein are techniques to generate a stereo sound signal based on direction of arrival of sound signals. A method includes receiving sound signals at a microphone, outputting a mono sound signal from the microphone, determining a direction of arrival of the sound signals with respect to the microphone, generating, from the mono audio signal, a stereo sound signal having a first channel and a second channel, wherein an amplitude of the first channel and an amplitude of the second channel are weighted, respectively, based on the direction of arrival of the sound signals at the microphone.

Abstract: Presented herein are techniques to enhance the audio portion of a video conference. In one embodiment, a method includes determining, using a multi-microphone array, a direction of arrival of sound signals from a user, detecting, using an image from a camera, a face of the user, determining a position of the face of the user with respect to a position of the camera, and forming a spatial beam for the multi-microphone array based on the direction of arrival of sound signals from the user and the position of the face of the user.