If you know that a well-known brand of smoke alarm sounds identical to a rare parrot, you may well be a fan of Chris Mitchell, CEO of Audio Analytic. His Cambridge-based company augments consumer technology with sound recognition. Just as speech recognition makes out spoken words, Audio Analytic’s sound recognition technology can tell the difference between the bark of a dog and the cry of a baby. “It’s the equivalent of a language model, but for sounds” says Mitchell.
AuditoryNET – Audio Analytic’s sound-recognition AI – has extremely broad uses. The company worked with German earphone manufacturer Bragi to produce AI earbuds that prioritise a user’s safety by recognising, for instance, an ambulance’s siren and alerting the user to the direction of its approach. The idea is to protect users from “all sorts of dangerous situations you find yourself in because you made yourself completely deaf in a city”, says Mitchell.
Audio Analytic has also embedded AuditoryNET in smart home devices such as the Hive Home Hub 360, which can detect the sound of smoke and carbon monoxide detectors, barking dogs, or windows being broken. AuditoryNET doesn’t need an internet connection to run – good news for the privacy-minded.
To train AuditoryNET’s algorithm, Audio Analytic used Alexandria, the world’s largest collection of audio data. “One of the things we’ve done recently is map out the entirety of our sound universe,” says Mitchell.
The company has created a sound map, comprising over six million audio files. It looks like a rainbow honeycomb: it visually represents similar sounds clustered together in coloured blocks, or “tonal islands”. Mitchell suggests turning down the volume when he gets to the “smashing” island. “This ‘break sound’ was from a dining room,” he says. “[The glass being broken] was a laminate wood pane of glass – and there are six other kinds of ‘break’ associated with it.”
Alexandria’s data pool of audio samples had to be built from the ground up. The stock sounds used in movies were useless, as they aren’t true to their real-world equivalents. “If you go and see the latest Avengers movie, I’m sure the Hulk will drop something on a car,” says Mitchell.
”That car alarm going off is not a real car alarm.” That sound would train AI on a fake reality: disastrous, if you need to detect someone breaking into a car. Therefore the company built its own lab to capture raw sounds, and sent out teams to record others in various environments. They even relied on networks of volunteers to come into the sound lab, or to use recorders to capture sounds in the real world.
Audio Analytic’s plans for the future are confidential, but its goals are clear: to continue to develop technology to identify sounds inside and outside the home. And to meet the challenges of birds that sound like alarms. “I doubt if evolution has conspired just to give me this problem,” says Mitchell. “But it’s a problem that has to be addressed.”
More great stories from WIRED
😡 TikTok is fuelling India’s deadly hate speech epidemic
🚀 The staggering power of Russia’s top-secret nuclear rocket
🍫 The foods you’ll really need to stockpile for no-deal Brexit
♻️ The truth behind the UK’s biggest recycling myths
🤷🏼 How is the internet still obsessed with Myers-Briggs?
📧 Get the best tech deals and gadget news in your inbox