I would like to know if Microsoft Speech API on Python supports multiple voices recognition. I saw the beta of SDK Speaker Recognition, but I was wondering if this feature was already in the Speech SDK or not.
I have checked all the python SDK methods documentation and searched over the web and stackoverflow if anyone ever needed/tried multiple voice recognition in speech-to-text using MS Speec, but I couldn't find anything about it.
When I transcribed an audio of a two persons conversation (a female and a male) using Microsoft Speech-to-Text, the recognized text was not split when the voice changes.
