- Vocal Familiarity -

In just the last few years, you can verbally shut down Xbox Kinects and Samsung Smart TVs; you can ask your smartphone to point you to the nearest gas station is; you can compose text messages by talking it out.

The point is speech recognition is becoming more and more common. But I've found that the accuracy is still pretty bad. By "pretty bad", I mean not 99% accurate. If it's not at least that accurate, I feel that I might as well type it out. As a sidenote, I have the same issue with predictive keyboards.

Considering there are a very limited number of pronounceable sounds (phonemes) in English, shouldn't we be able to vastly improve speech recognition by asking the user to speak out every phoneme as set-up?