This is being done using various types of networks. See these slides on image captioning by Karpathy for an example using a CNN and RNN: http://cs.stanford.edu/people/karpathy/sfmltalk.pdf
If we're going with a brain metaphor. What would be the those neural networks' version of synesthesia?
Feeding mp3s to an image recognition neural net. And as soon as I typed that, I want to try it.
Actually, in the architecture you described, if there is a planning net that's connected to image net and an audio net, rather than feeding audio to the image net I think synesthesia would be better modeled by feeding the output of the audio net into the image net's input on the planning net. If that makes sense.
Not the output. Making several single connections from intermediate layers from the different nets.
CNNs can actually be used for audio tasks too, on spectrograms
It seems like the way forward would be networking together various kinds of neural networks to achieve complex goals. For example, an NTM specialized in formulating plans that has access to a CNN for image recognition, and so on.