They did post the code on github (https://github.com/Microsoft/CNTK) with the Microsoft open source license.

Presumably you could feed it speech from a running instance of gnu-radio.

CNTK is just a toolkit, like tensorflow or theano. Code for the paper was not published.

Let alone the datasets used to train, which are worth a lot of money.

Aussie company (Appen) provides the datasets :D

That's the one that seems to be using illegal GCHQ wiretaps ... see the (Dutch) article below about an Appen translator getting a private voicemail of her ex to translate.

http://www.volkskrant.nl/tech/privegesprekken-van-duizenden-...

No, it's GCHQ contracting Appen. They only deliver the platform for distributed outsourced transcription.

I guess it would come in https://www.cris.ai/

The novel elements of this have already been released individually, particularly the lattice-free MMI training which can be run through Kaldi's nnet3 configuration.

Also, don't assume that a 0.4 % increase means drastically better real-world results. This dataset has been around longer than I have, so by this point Microsoft has just gotten really good at tuning.

Open source Kaldi gives you 7.8%, not very far from 5.9, you can check the thread from the discussion of the first version of the paper https://news.ycombinator.com/item?id=12502119

Or even mock emergency calls where the callers aren't in a rational state of mind.