you should probably read the article, it's different than other methods:
What makes the attack different compared to other approaches is that it can reach a typing prediction accuracy of 43% (on average) even when:
-the recordings contain environmental noise -the recorded typing sessions for the same -target took place on different keyboard models
-the recordings were taken using a low-quality microphone
-the target is free to use any typing style
still only useful in extremely limited situations though... but it is neat that it uses timing of key strokes over the different sounds of each one...