I’m looking for advice on how to add speaker independent voice recognition without having to use a ‘wake word’. Being able to say custom one word commands to control the device.
An internet search will turn up a few Arduino-compatible voice recognition modules, with very limited capabilities.
From what I’ve seen they all require a wake word. Unless that’s something you can just throw out in the code?
Well that's not very helpful. Can you post an article that you found with your internet search or are you just assuming?
Any luck? I'm looking for this exact same thing
I remember a Raspberry Pi project in the MagPi magazine to do exactly that. It was in an Issue of the MagPi magazine, but I can't remember if it was an actual how to do it tutorial or a report on a group trying to do this.
However adding "Raspberry Pi" to your search terms might just bring some good results.
Or you could try and do it with a Nano BLE and this link:-
AI - Google’s flagship machine learning library: “TensorFlow“
I do have a note that :-
Recognising different sounds using AI was in MagPi #98 page 30. Free downloads of back issues are available. But this was not the project I was thinking of when I first mentioned the Raspberry Pi first in this post.
This topic was automatically closed 180 days after the last reply. New replies are no longer allowed.