Where to start for Arduino Voice Recognition and identifying multiple voices?

Using Arduino Project Guidance
#1

Hi there, this is not my first Arduino rodeo, but it is my first time asking for help on the forum. I apologize if this isn't the appropriate place to post this, please redirect me if so!

I'm working on a project that involves recording speech, transcribing it into text, and displaying it on a screen. I haven't ordered any modules yet, but I've done some research into libraries and couldn't find any that both transcribed user speech and could also differentiate between different speakers.

Are there any accessible libraries or resources that are able to identify different speakers when taking voice input? Let me know, thanks!

#2

Welcome.

An Arduino is no where near powerful enough for this kind of thing. Possibly a Raspberry Pi, not sure.

#3

We can't get Alexa from amazon to work 100% - and they spent millions on development.

Even 'Dragon Dictate' from the 2000's was a pain, even with a single user.

#4

Where to start?

Not with an Arduino!

#5

Frequently, even humans cannot separate multiple simultaneous speech streams. If you succeed, you should be up there having dinner with Bill Gatea.

#6

This topic was automatically closed 120 days after the last reply. New replies are no longer allowed.