This sample demonstrates how to use the Kinect sensor and how to use the Join() operator to synchronize streams. The sample uses the
Kinect's face tracking and the audio and video streams to detect when a user is speaking. The sample compiles and runs on Windows.
In order to run this sample, you must have a valid Cognitive Services Speech subscription key. You may enter this key at runtime, or set it in the static AzureSubscriptionKey variable on the OperatorExtensions class. For more information on how to obtain a subscription key for the Azure Speech Service, see https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/get-started