-
Notifications
You must be signed in to change notification settings - Fork 86
Depends. You can train each word, but because one normally speaks single words a bit different than a sentence or two words one after another you may want to test this out by yourself.
Does one get better accuracy if words are completely different, e.g. 'play' + 'stop' instead of 'play' + 'pause'?
Not necessarily, SOPARE can differentiate such words quite well.
SOPARE has no built in support for prefix words. Train normal and write a custom plugin where you do something special with some words/sounds.
A single word is triggered e.g. when knocking on a table, what should one do or look into to prevent this?
This is called a false positive. It can be prevented with better training, a different (better) microphone, or different settings. Also take a look at https://www.bishoph.org/sopare-precision-and-accuracy/.
[[MIN_CROSS_SIMILARITY, MIN_LEFT_DISTANCE, MIN_RIGHT_DISTANCE, START_POS, LENGTH, u'PREDICTION']]
A token is a single entity from a sequence that (in best case) can be encountered again under similar circumstances. Here is a blog post that hopefully sheds some light into this: https://www.bishoph.org/smart-home-and-voice-control-sopare-beta-testing/.
Yes, as follows:
sudo apt update
sudo apt install python-pip
pip install numpy
pip install scipy
sudo apt-get install python-pyaudio
pip install matplotlib