The invention provides a video conference tracking system and method based on a microphone array. The video conference tracking system is characterized in that the system comprises a camera for acquiring video conference image information; the camera is installed on a rotary table driven by a motor; the motor is controlled by a controller; the controller is connected with the microphone array forimplementing sound source positioning; and the controller acquires a position of a speaker according to the microphone array and controls the motor to drive the camera to rotate so as to implement tracking on the speaker. The video conference tracking system and method have the effects that the microphone array is adopted to carry out sound source positioning; by acquiring a direction and a distance of the speaker and combining a focal length regulation function of the camera, automatic regulation on a direction and a focal length of the camera is sufficiently implemented; and the system is simple in structure, convenient to control and rapid to respond, and meets the tracking requirements of the speaker in a video conference application scene.