How Siri (Really) Works
Siri is not magic obviously, and I hope that’s not what you think it is. Nevertheless, it’s still tremendously incredible. The complexity behind Siri is definitely non-trivial in any sense. I know (well, not that I know a lot to begin with) because I’m currently working on something related to this, but of course nowhere near the scale of this monster project.
Not surprisingly, the crucial part of Siri that determines whether it can deliver what it’s promising, is really the speech-to-text analyzer. Translate that to simple words: can Siri convert what you speak into words accurately. If it’s a yes, it’s a straight winner. And here’s how Wofford puts it across (and note the keyword there, “RELATIVELY modest”):
If it can understand me, it will work. The grammatical analysis and service providing parts of the system are relatively modest in terms of technical difficulty and I suspect Apple has these in hand.
Lastly, another reality check:
What I hope you’re seeing is that what Siri does isn’t science fiction and it certainly isn’t magic. It is the old and still-developing technology of speech-to-text analysis and the old and fairly mature technology of simple grammatical analysis and string matching.
