In example implementations, a system is disclosed for suppressing ambient sounds. In one example, the system includes a camera, a plurality of microphones, a plurality of speakers and a processor. The camera captures an image of a target, the plurality of microphones receives ambient sounds and a plurality of speakers outputs an audio signal to suppress the ambient sounds. The processor is in communication with the camera, the plurality of microphones and the plurality of speakers. The processor can identify a location on the target based on the image that is captured, determine a direction and a frequency of the ambient sounds, and generate the audio signal based on the direction and the frequency of the ambient sounds, the audio signal is directed towards the location on the target.