I want to know how Alexa recognize the audio stream from Amazon Alexa DDK, like Amlogic. For example:
- I say "Alexa, what is the weather today?" to the Alexa DDK. The device convert the voice to binary audio stream and sent to AVS.
- AVS recognize it and provide response.
I want to know how Alexa recognize the audio steam. Does Alexa call Amazon transcribe API convert the audio stream to text and then analyze it?