I want to build a device/service that relies on being able to recognize different voices (identities) when given some audio input (ex: conversation, lecture).
It needs to be able to tell that Person A, B, or C is speaking while listening to some audio input (of course, I plan to have their voice profiles? registered before hand).
I couldn't really find such a service in Alexa Voice Service or something else offered by Amazon Developers.
If such a feature exists, I would really appreciate it if you can provide me with a link.
Thanks in advance!