As Apple rolls out Siri beyond the iPhone and into shared devices like the iPad and, most recently, Apple TV, Cupertino’s engineers have been working on a way of letting its voice activation technology pick up individual users, and offer them customized options based on their past preferences.
Published today as the patent “User profiling for voice input processing,” the technology would allow Apple to make better use of Siri (and voice recognition in general) as it moves into new fields like home automation and vehicles.
Apple’s patent describes how it would identify, “a user providing a voice input, and process…the input to identify a corresponding instruction based on the user’s identity. In particular, this is directed to processing a received voice input using the subset of library terms used to process the voice input.”
Being written in patent-ese, the wording is written as broadly as possible, but it essentially covers the concept of recognizing users and then offering them different options according to their previously-expressed preferences — for example, different music playlists.
Apple’s not the only company to explore this kind of technology. Google Now recognizes different accents from users and switches accents accordingly, while a number of companies (including Apple) promise that their voice recognition systems can be tuned to one particular user’s voice.
I’ve never found these latter technologies work as well as they could, but if Apple could hammer out the underlying tech (which it may be able to do thanks to its growing Artificial Intelligence ambitions), I can definitely see a use for today’s patent.
We’ll be thanking Apple when our Apple Car is able to immediately modify its seat position, radio station and air-con just from hearing you say “Good morning.”