Can speech recognition software handle accents?

An interesting article on Slate.com looks at whether the new iPhone’s speech recognition software can handle different accents.

The question is particularly important since the phone has the capability to be used in any country in the world. And the answer is yes, due to programmers ‘training’ the system. This is done by feeding in lots of audio and then typing in what is said – the software then ‘learns’ to recognise different forms of pronunciation.

From the article:

Take, for example, the plosive consonant T, which sounds one way in the word tree and another way in the word plate—and that’s just in one dialect. When software engineers are working on a product that will be used by people around the world, they include recordings in different dialects and from non-native speakers of English in the training. To stick with the T example: British people tend to pronounce the T sound in butter much more clearly than Americans, who swallow it. Eventually, the program establishes a kind of bell curve for the phoneme, and it will interpret any sound whose frequencies and other physical characteristics fall within the parameters of that curve as a possible attempt to produce that phoneme. (Source: Slate.com)

The software then uses the curve to guess what a word is when it is not pronounced clearly. Pretty cool huh?