| 摘要 |
A soundbar comprising a plurality of speakers that outputs audio content to a listener and a camera that captures and analyses images of the listener to determine a characteristic of the listener, wherein a response of the listener to media content including the speaker audio output is detected using the camera. The speaker output is also controlled based on the listener characteristic(s). Data items comprising a user characteristic and the detected user response, such as mood and body language, may be stored locally or transmitted over the internet to a remote store. User response may be detected for media content associated with an advertisement, news item or entertainment programme. Image processing of captured images may determine the age or gender of the user, and facial recognition may determine a predefined listener having a respective user profile that may comprise the users preferred volume range, audio/video style, language, interests or restrictions (for censoring media content). The soundbar may be coupled to a display for outputting A/V content. Video content may be controlled based on a viewers characteristics or detected gaze direction. The soundbar may determine a plurality of users, with separate audio controls for each user. |
