Sitting at home in front of the TV could soon become an altogether more sociable experience. A new iPhone app can identify the show you’re watching just by analyzing a few seconds of audio, making it possible to automatically share your TV viewing choices with friends through Facebook and Twitter. It only does this when the user presses a button to activate it.
People often talk about what they watched the night before, so TV viewing already has a social element to it, says Adam Cahan, founder and CEO of IntoNow, the startup company that makes the app. “What we’re focused on is how to connect people through the shows that they love,” he says.
Using a technology called SoundPrinting, developed and patented by IntoNow, the app allows people to instantly see what their friends are watching, and discuss them through social networking functionality, all while the shows are still on the air, says Cahan.
IntoNow uses software that carries out a spectral analysis of audio to create unique identifiers of TV content that can then be indexed and searched quickly. “Our catalog covers anything that’s been on TV within the last five years,” says Cahan. That equates to 140 million minutes or 266 years of content, he says.
Other smart-phone apps use audio tagging to identify music. London-based Shazam, for instance, can identify 10 million songs based on a few seconds of music per song.
IntoNow, however, can also identify shows that’s haven’t aired before, says Cahan. “You can identify a new episode of Dexter or breaking news, even,” he says. “We did it with the Super Bowl this weekend.”
This is possible because IntoNow continuously monitors the broadcasts from 130 TV channels, carrying out a spectral analysis of the audio 20 times a second, says Rob Johnson, the company’s technology architect. So when someone uses the app, even new shows should already be in the system.
“When [the app] searches the index, it doesn’t tell you what program it was,” he says. Instead, it delivers the channel and time at which that segment was aired, and from this, the system can work out the precise program and episode that was being watched.
Others are also looking at identifying TV content in this way, says Marie-José Montpetit, a pioneer of social TV at MIT. Recognizing live broadcasts is an advance, she says: “It’s a nice gadget that could take off.” But she doubts it will fundamentally change the way we watch TV.
Even so, it could change the way advertisers operate. Cahan says the information collected by IntoNow could be used to determine what part of a show people are watching. He adds that “it gives you the ability to say ‘I’m into that commercial.’ ”
An app that records audio from the living room may raise privacy worries, says Montpetit. But, according to Johnson, there is no risk of anyone being able to eavesdrop on users. “We are not recording the audio, we are analyzing it,” he says. “So there’s no way to reconstruct that audio.”
DeepMind’s cofounder: Generative AI is just a phase. What’s next is interactive AI.
“This is a profound moment in the history of technology,” says Mustafa Suleyman.
What to know about this autumn’s covid vaccines
New variants will pose a challenge, but early signs suggest the shots will still boost antibody responses.
Human-plus-AI solutions mitigate security threats
With the right human oversight, emerging technologies like artificial intelligence can help keep business and customer data secure
Next slide, please: A brief history of the corporate presentation
From million-dollar slide shows to Steve Jobs’s introduction of the iPhone, a bit of show business never hurt plain old business.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.