They don't need to actually understand - whatever that means - they can apply statistical models based on phonetic distances and large corpora of dialogue.

Has that worked so far?

Google voice search will make several guesses as to what I said. It will sometimes enter a nonsensical, but similar sounding phrase to what I intended into the text box, but will then figure out that it's first guess is nonsense and return the correct search result.

So just based on observation I would say it works pretty good. On mobile I almost always use voice search, and unless I'm searching for an italian name or something weird it almost always hears me correctly. Even in a noisy pub.

That's a good point, I've rarely had issues with Google voice searching.

Of course it has. We went down from 40% to 6.9% error rate in 26 years. It may take a couple of decades to get to 0.1%.