Language services like LUIS have been working but speech and video services needs to be more stable.
What do you like best?
Detailed documentation and easy to use web and command interface. Most of the results have been accurate.
What do you dislike?
Less control to customize the services to our requirements and buggy updates to CNTK SDKs which sometimes breaks the production code.
Recommendations to others considering the product:
I highly recommend this to my colleagues and all others who wants to explore and get started with AI/ML services. This is backed by Microsoft which has vast set of training data and evolving continuously.
What problems are you solving with the product? What benefits have you realized?
Building next generation conversational Bots with advanced natural language capabilities and speech support which also handles chitchat and FAQs.