I am performing a POC on Voice Bio-metric Authentication via Cortana in Windows 10. I would want to know if there is a way to retrieve the voice input provided to trigger Cortana (either in wav or BLOB format), using which I would trigger a 3rd party API to validate the voice input provided against a pre-enrolled voice.
For Example, say I invoke my application using “Hey Cortana, Launch My Application”. I need this particular voice input(either in wav or BLOB format) to be sent to a bio-metric service which recognizes the user based on his voice.
Your inputs are highly appreciated.
This information is transient (and protected) for privacy reasons. But it doesn't mean your own application could not put the appropriate protections in place and customer notifications to do something similar. The Bing speech API does support speech to text: https://learn.microsoft.com/en-us/azure/cognitive-services/speech/home. With LUIS, you can also use its language identification. :-)