Researchers at Google Labs are working on an interactive television application that provides contextually relevant web content for viewers.

The researchers have demonstrated how to sample the ambient sound emitted from a TV and automatically determine what is being watched from a small audio signature.

The system uses a microphone to analyse the sound and can then provide the user with related web content.

For example, during a time-out in a live sporting event some viewers may enjoy reviewing highlight footage, while others may prefer to view a parallel programme to watch player profiles and statistics before being automatically returned to the sporting action once the event is back underway.

Google Labs claimed that the system could keep up with users while they channel hop, presenting them with a real-time forum featuring a live political debate one minute and an ad-hoc chat room for a sporting event in the next.

All this would be done without users ever having to type in or even know the name of the programme or channel being viewed.

"Taking this further, we could collect snippets from the web describing the actors appearing in a movie, or present maps of locales within the movie as it takes place, regardless of whether it is a live or recoded broadcast," the researchers said.