A set-top box device comprises a speech recognition module, a video image recognition module, and a voice over Internet protocol bridge. The speech recognition module is configured to perform speech recognition on a voice command signal to determine an action to take in the set-top box device. The video image recognition module is connected to the speech recognition module, and is configured to recognize a display device image. The voice over Internet protocol bridge is coupled to the video image recognition module, and is configured to connect a voice telephone call from the set-top box device to a call center.