Send raw query with request
Currently all skills must run through Amazon’s Natural Language Understanding and provide a language model to Alexa. While this is helpful for getting started, many more advanced features for Language Processing and response building benefit heavily from having the user’s speech accessible to perform more complex operations like sentiment analysis, conversation reconstruction or custom natural language processing through models on other services. This allows developers to deliver a richer experience to users through the additional processing it makes possible.
For my use case in specifically it would be acceptable to have an option in the console to disable the language model and only receive the speech transcript in requests, and I think there are other developers who would benefit from this as well. Currently to get access to an approximation of the raw speech requires a basically empty language model, which works but suffers in performance.
Thanks for the clarification and suggestion! We’ll route this to the appropriate internal team for review.
Robert Oschler commented
This is even more troubling when you realize the Alexa Prize university developers have access to a more sophisticated input stream than the rest of us developers do. Please at least move the input data the Alexa Prize teams have access to, to the general availability category ASAP.
I second this suggestion. There're a ton NLP features we'd like to implement, but with the current infrastructure, it's just impossible.