Have you ever gotten an important phone call while in a crowded bar, but were unable to answer it? The lovable fanboys over at Patently Apple say that Cupertino is on the case, working on tech that could make its way into a future iteration of the iPhone. A pair of patent applications shows how Apple is hard at work on both text-to-speech and speech-to-text converters that could make it possible for you to answer the phone in that crowded bar–or, for that matter, in a pin-drop quiet library.
So let’s play out, first, that scenario of the crowded bar. You’re at O’Malley’s, and you get that phone call from your grandmother that you just have to take, even though Bon Jovi is blaring in the background. So you pick up the phone, and here’s where Apple’s tech would kick in. First of all, the iPhone could be smart enough to detect that the noise level is so great that you can’t hear her, and she can’t hear you. The phone could then automatically activate, or prompt you to activate, a text-to-speech conversion mechanism. (It could also play a pre-recorded message for grandma explaining the situation to her, and the weird technological game that’s about to ensue.)
You would then start, essentially, texting your grandmother instead of speaking to her. Apple’s text-to-speech tech would then play back what you’re saying to her, presumably more or less instantly. Grandma could then text you back. And if she doesn’t have a cell phone? No worries, Apple’s patent envisions working the inverse, as well: your grandmother could simply speak into her old rotary phone, and Apple’s servers would convert that into text for you to read at the pub.
Apple applied for a second, related, patent, too. Say you’re in the library or another quiet place, and you want to answer that phone call but need a few seconds before you can get into the hallway to speak. The other patent introduces the idea of an “incoming call hold mechanism.” Get a call, press the relevant button, and the call will be answered but immediately put on hold, together with a pre-recorded message telling the person on the line to sit tight while you’re getting to a situation in which you can speak.
Voice recognition is anticipated to be a large part of the next generation of iOS; Apple acquired Siri, the makers of a “virtual personal assistant” that relies on voice recognition tech, and reports recently emerged to the effect that Apple was in big negotiations with Nuance, leaders in the voice recognition space. It’s not clear whether the newly spotted patents are directly related to Siri or Nuance, though presumably the technology would all be integrated.
Five poems about the mind
Work reinvented: Tech will drive the office evolution
As organizations navigate a new world of hybrid work, tech innovation will be crucial for employee connection and collaboration.
Investing in people is key to successful transformation
People-related factors like talent attraction and retention and clear top-down communication will determine whether your transformation progresses or stalls.
The way forward: Merging IT and operations
Digital transformation in any industry begins with bridging the gap between two traditionally separate teams.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.