Renaissance Technologies

4848.107 - 4872.863 Ben Gilbert

Right. Speech recognition is a hidden Markov process where the computer that's listening to the sounds to try to turn it into language doesn't actually know English, right? Obviously. But what it does know is when I hear this set of frequencies and tonalities and sounds, there's a limited set of likely things that could come after it. And in Greg's book, he greatly points out this perfect example.