-3

I would like to know if is possible create a service with Cognitive Services of Windows Azure that allow me to recognize one specific sound in a conversation (provided by a live stream in internet) and how make it. I already know basic techniques of Machine Learning, but I never implemented something like this, anyway I would like to use Cognitive Services to make it in a simple and efficient way. This task will be linked with other task like a chain of events, so I should use something that provide SKD for java or Python. Did somebody know how can I make it? Thank you!

minimanimo
  • 35
  • 1
  • 2
  • 9

1 Answers1

1

Now, there is a new preview cognitive service named Speaker Recognition API, which you can use it to implement your needs for recognizing a specific sound in a conversation, please see the offical overview to know the details. And there is only REST APIs for this service by now, not SDKs for specific programming languages like Java/Python. So please move to the REST API reference website to learn how to use it.

Hope it helps.

Peter Pan
  • 23,476
  • 4
  • 25
  • 43