Because in the long run the keyboard must inevitably be looked back on as a clumsy, anachronistic input device.
"A keyboard. How quaint."
I really don't see voice becoming the primary input mechanism for most computer users unless there are a whole lot of advances in AI under the hood. Speech between two humans is an efficient mode of communication only because humans are able to infer what should fill in the gaps. Even then, it's easily misunderstood; without miscommunication and wrong conclusions, we would have no basis for sitcoms.
If speech control of computers is based on crisp, sharply articulated commands issued in a consistent and logical temporal order every time, I don't see it replacing the keyboard (or mouse, or even handwriting) without a change in the programming philosophy behind it, not just the application of more computing horsepower under the hood, however impressive that horsepower may be.
I really don't see voice becoming the primary input mechanism for most computer users unless there are a whole lot of advances in AI under the hood. Speech between two humans is an efficient mode of communication only because humans are able to infer what should fill in the gaps. Even then, it's easily misunderstood; without miscommunication and wrong conclusions, we would have no basis for sitcoms. Nice example; I take your point - but I do expect to see AI make a comeback at some point, exactly because of the high value implicit in it.
If speech control of computers is based on crisp, sharply articulated commands issued in a consistent and logical temporal order every time, I don't see it replacing the keyboard (or mouse, or even handwriting) without a change in the programming philosophy behind it, not just the application of more computing horsepower under the hood, however impressive that horsepower may be. I would cast the situation this way: people communicate by a combination of verbal speech, inarticulate grunts, eye contact, body language, and hand gestures. The mouse/keyboard system is strictly one of hand gestures - and IMHO that is a highly restrictive and blinkered way of doing it. Naturally Speaking takes a whack at pure verbal communication, and guess what - humans have experience at strictly verbal communication, too. Telephone conversation is one such model, and that would still be quite an AI challenge for a computer. Naturally Speaking tries for a different model - one which puts me in mind, not of a free-form phone chat but of military/aviation radio comm. Including the ability to use The NATO phonetic alphabet: Alpha Bravo Charlie Delta Echo Foxtrot Golf Hotel India
Juliet Kilo Lima Mike November Oscar Papa Quebec Romeo
Sierra Tango Uniform Victor Whiskey Xray Yankee Zulu
It goes so far as to enable verbal mouse position commands and clicks. Obviously an able-bodied person will prefer typing to verbalizing "Alpha Bravo Charlie Delta Echo." Naturally Speaking falls short, precisely because it needs more (if indeed it has any) AI. But for the seriously disabled, it's better than nothing. The application I set it up for showed that using an IR tracker to follow head movement was vastly superior to verbal articulation of mouse pointer position. But the capability Naturally Speaking does exhibit strongly suggests that its outputs would be adequate inputs to an AI program which actually could parse dictation efficiently. I do not consider that user input should be limited to verbal comm - but it certainly could be an improvement to the system if it included it. Very few of us type as fast as we speak. And very few of us speak as precisely as we type - because we use the backspace key. At least, I do . . .
IMHO an interface which exploits both verbal dictation and digital gesturing via one or two small "keyboards" will one day supplant the keyboard/mouse paradigm. And I think it will be a big deal when it hits the market. You mentioned "handwriting" - and that is the very last thing I would try - it has the worst features of verbal and of gesture communication, and the best features of neither.