Multiple speaker voice recognition

Lot of software programms can transcribe voice to text but only from one "voice".

But, few recent software try to transcribe voice from multiple speaker to text, some with few hours of "calculation", other in real time.

What kind of algorithm can they use to transcribe more than 1 voice ?

Can you tell me some name of different projects about multiple speaker recognition software / algorithms ?
Sign In or Register to comment.

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!