Best wake word / setup?

Have been using Jarvis but it gets a high amount of false wakes with the TV on, seems to trigger on anything with a few “SSS” sounds in it.

Tried Alexa for a laugh and its still false-waking, not as bad but still there.

Is there a good setting for sensitivity, can’t seem to find much out about that setting in help.

Prob porcupine Dave, but it a ‘clean’ dataset that doesn’t accept much noise (prob recorded with a high quality clean mic with no background noise addition)

Comes with a few wakewords but to train yourself means opening commercial services.

Mycroft precise would likely be the best as really accuracy is down to the dataset recipe you feed it.
It uses an old full tensorflow that if they updated and used a different method it would run 10* lighter or faster and if shifted to 64bit its gets another *2 so 20 times lighter than it is.
Its classification structure isn’t great and the proposed training methods are fubar as tensorflow-kws is state-of-art but the average results are usually poor with Precise.

Ok thanks, ill stick with Porcupine

Is there any point/benefit fiddling with sensitivity ??

Yeah if you get it right prob with porcupine is it doesn’t return the hit sensitivity just a yes or no if the KW has been detected so its quite hard to tune without trial and error.

Hmm, will try.

0= strict and 1= loose ???

Its fractional I think 0.0-1.0 but getting the last result would make things much easier.

To be honest I am a bit bemused about KWS as for a long time the options have been poor.
I get Raven is a quick setup that captures KW to make datasets but its actually doesn’t capture the following command sense so sort of becomes this limited low accuracy KWS.

Google published a repo of state-of-art kws and they are extremely accurate and lite running under tensorflow lite.
Opensource that you can train yourself and if you get the dataset right wow they are pretty amazing where the only problem is your KW will be recognised under high noise but the command sentence to ASR likely not and maybe why there was never a push for better as it just shifts the cul-de-sac higher up the process tree.

An accurate wake word recognition would be about 90% good - I had it set to reduce the volume on the tv once woken but the false triggers meant the volume would down too many times without reason :slight_smile:

Its WER Word error rate but I get the feeling PV ran that test in pretty clean conditions.
Pocketsphinx and snowboy (retired and now given free as open source) are pretty poor KWS by todays standards.

Validation of KWS models have state-of-art pushing 98% on benchmark datasets such as the Google commandset which contains much variation and bad data(10%) to create a benchmark dataset as all would return 100%.

With custom datasets (record your own) its relatively easy to garner 100% validation and create noise tolerant models.
I can have 70dB noise (music or voice) and as long as I raise my voice to similar level a modern model such as a CRNN will actually detect.
I dunno if all streaming KWS use many inferences @ 20ms but in my tests even a simple sum of the inference envelope rather than singular snapshots of a threshold means its also extremely low in regards to false/positive negatives, false negatives are not a problem as often its just resay that KW maybe louder / more clearly. If you train right and use a more modern model it will make porcupine look as antiquated as it does snowboy & pocketsphinx.

Still the problem from there is KW is recognized but ASR not so much.

Thanks for that, its fascinating stuff but a fair way over my head :slight_smile:

I keep reading “Picovoice”, “PyCroft”, " MyCroft" and some others i think, are these competing projects or parent projects etc to Rhasspy ??

I think its Pycroft that pops up most but is very small on information etc as to what it actually is or does :slight_smile:

Mycroft (pycroft) which is competing I guess if such a thing, accuracy wise prob not much difference but has a extensive skill repo the KWS Precise is from Mycroft and a bit of an oxymoron.
If they spent as much time updating there core than shiny web page presentations it could be great but IMHO there is a thick spread of somewhere between optimism & snakeoil, the guitar toting ex ceo and his ballad of the patent troll had me running.

There is an element of ‘gold rush’ AI to these projects whilst really the prospecting days are over and essential skills lacking in an extremely in-depth field.

Thanks, i agree with the web page stuff - very polished but lacking content :slight_smile:

I’m sticking with Rhasspy :slight_smile: