It seems to me that images and sounds are 'alike' in a way that doesn't (on its obvious face) expand to include Atari game strategies and evaluating Go positions. In which case generalizing across the latter gap is more impressive than a single algorithm working well for both images and sounds.
The difference isn't easy to describe, but one such difference would be that a single extra stone can change a Go position value much more than a single pixel changes an image classification.
The difference isn't easy to describe, but one such difference would be that a single extra stone can change a Go position value much more than a single pixel changes an image classification.