But I believe these only try to recognized words from sound. I doubt it can make conclusions with the complexity Robert told us about or even close to that.
If you are more specific in using deep learning model for speaker recognition, I would suggest starting with Honglak Lee work. His Matlab code is available from his homepage.
Hi. If you are looking for the tools themselves in order to build a speech recognition system, I recommend looking into Kaldi. It supports deep learning as well. Here is the website: