loading...

re: Acoustic activity recognition in JavaScript VIEW POST

TOP OF THREAD FULL DISCUSSION
re: Okay, one question. low-frequency whistling = brushing teeth. How does this happen? Does the software recognize frequency, or it also recognizes...
 

I didn't train it with whistling so it's predicting whatever is closest to what it was trained with, which must be brushing teeth in this case.
It's looking at all the data coming from the WebAudio API

 

Yep. I asked if it is trained for frequency or the tone? or both?

If by tone you mean notes, notes are named frequencies.

The data you get back from the WebAudio API is the frequencies picked up by the microphone copied into a Uint8Array using the getFrequencyByteData method on the AnalyserNode.

By tone, I meant tone: which makes a C note from violin and piano distinct.

However, I got what you meant. Nice and creative work!

Notes are just particular frequencies that are given a name. In any case, the tone you're using is a bit off.

Traditionally, that's referred to as timbre. It's the volume of specific frequencies in a note's harmonic series that account for differences in timbre in pitched instruments. Here's a great video explaining how that works.

Code of Conduct Report abuse