For my personal projects, I often get inspired by research papers I read about human-computer interaction.
Lately, the one I've been looking into ...
For further actions, you may consider blocking this person and/or reporting abuse
Okay, one question.
low-frequency whistling = brushing teeth.
How does this happen? Does the software recognize frequency, or it also recognizes the tone?
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.
Awesome post! Kudos for making such an interesting experiment with JavaScript 👏 👏 👏
Actually, my team just completed an open-sourced Content Moderation Service built with Node.js, TensorFlowJS, and ReactJS that we have been working over the past weeks. We have now released the first part of a series of three tutorials - How to create an NSFW Image Classification REST API and we would love to hear your feedback(no ML experience needed to get it working). Any comments & suggestions are more than welcome. Thanks in advance!
(Fork it on GitHub or click🌟star to support us and stay connected🙌)
Amazing!! Your side projects are always awesome
This is super cool! An awesome intersection of a bunch of different things I've been wanting to play with. Thanks for putting this together.
Impressive
Really cool @devdevcharlie !
Nice work, trying to remake this for practice purposes, how do I go about it ?
Thank you. I used this tutorial and was able to create my own acoustics activity recognition app for detecting drones anthonyofboston.github.io/