At the time of writing, the Custom Recognition Intelligent Service (CRIS) is still at the private beta stage. As such, we will not spend a lot of time on this, other than going through some key concepts.
When using speech-recognition systems, there are several components working together. Two of the more important components are acoustic and language models. The first one labels short fragments of audio into sound units. The second helps the system decide words, based on the likelihood of a given word appearing in certain sequences.
Although Microsoft has done a great job creating comprehensive acoustic and language models, there may still be times when you need to customize these models.
Imagine you have an application that is supposed to be used in a factory environment. Using speech recognition will require acoustic training of that environment, so that the recognition can separate usual factory noises.
Another example is if your application is used by a specific...