Abstract: Systems and methods for audio management are disclosed. A conference device receives a plurality of audio signals comprising a first subset of audio signals originated inside an acoustic fence and a second subset of audio signals originated outside the acoustic fence. The conference device generates an in-beam signal based on enhancing the first subset of audio signals and suppressing the second subset of audio signals. The conference device generates a reference signal based on enhancing the second subset of audio signals and suppressing the first subset of audio signals. The conference device generates one or more masks based on the plurality of audio signals, the acoustic fence, and the reference signal. The conference device applies the one or more masks to the in-beam signal to suppress the second subset of audio signals originated outside the acoustic fence to obtain an output audio signal.

Abstract: For online audio/video conferencing applications deployed in an open office environment, using shared conference devices, it can be advantageous to define an acoustic fence. A non-participant audio received from outside the acoustic fence can be considered noise and filtered out before transmission of an audio signal to a far end recipient. Three suppression stages are used to filter the non-participant audio. The first suppression stage uses beamformers for suppression. The second suppression stage is mask-based, and the third suppression stage is reference-based. The three suppression stages filter out non-participant audio signals, having a wide range of frequencies.

Abstract: For online audio/video conferencing applications deployed in an open office environment, using shared conference devices, it can be advantageous to define an acoustic fence. A non-participant audio received from outside the acoustic fence can be considered noise and filtered out before transmission of an audio signal to a far end recipient. Three suppression stages are used to filter the non-participant audio. The first suppression stage uses beamformers for suppression. The second suppression stage is mask-based, and the third suppression stage is reference-based. The three suppression stages filter out non-participant audio signals, having a wide range of frequencies.