| 摘要 |
Embodiments are directed towards a speaker/microphone system. Each microphone in a microphone array generate an audio signal based on sound in a physical space. The microphone array may be arranged to logically define the physical space into a plurality of regions that have a status of active or inactive. An output signal may be generated from the audio signals, such that directional noise reduction is performed on audio signals associated with inactive regions and speech enhancement is performed on audio signals associated with active regions. A region's current status may be modified to its opposite status based on a request provided by a user. The request may be triggered by an activator or a spoken word/phrase provided by the user. An indication may be provided to the user regarding each current status for each region. The indication may also represent a quality of audio signals associated with active regions. |
