Siri may soon recognize different voices

By

Siri may soon be able to identify your voice and give personalized responses.
Siri may soon be able to identify your voice and give personalized responses.
Photo: Apple/Cult of Mac

Apple engineers are preparing for the day Siri can reliably recognize voices. They’re working on how this digital assistant will respond to requests from multiple users.

This issue became important with the release of Apple’s HomePod earlier this year, as smartspeaker are used in shared spaces.

The special chip built into Apple’s devices that recognizes the “Hey Siri” activation phrase is already supposed to filter out other voices. But this function is only used now in an attempt to prevent false positives — having the phone ignore another person saying the activation phrase. Still, it means Apple is closer to being able to identify individuals than many people think.

What if Siri knows who you are

When SIri was only used on a phone or laptop the system only had to worry about one voice and a single user. But smartspeakers, by their very nature, are meant to be shared. 

A new patent filing describes Apple’s thoughts on how Siri could deal with multiple users. The abstract for the filing says, in part, “This is directed to receiving a voice input and identifying the user providing the voice input. The voice input can be processed using a subset of words from a library used to identify the words or phrases of the voice input. For example, the subset can include one or more words related to media items selected by the user for storage on the electronic device, names of the user’s contacts, applications or processes used by the user, or any other words relating to the user’s interactions with the device.”

In less stilted language, after Siri has recognized your voice, you’d be able to order it to “Call John,” and it would know to call your friend, not your son’s friend who had the same first name.

Coming soon?

Apple requested its patent for “User profiling for voice input processing” in April 2017, back when the HomePod was still in development. It was awarded today (patent 10,049,675).

It’s quite possible the company’s engineers have made further progress in the intervening year and a half, and the next version of the HomePod will include this feature. The first version of Apple’s smartspeaker isn’t doing all that well.

That said, not every patent awarded goes on to become a product. Apple could have been exploring an idea that it won’t actually add to Siri.