Slashdot Mirror

← Back to Stories (view on slashdot.org)

Whistled Platform Upgraded With Word Recognition

Posted by Unknown on from the light-switch-kree dept.

An anonymous reader writes "A few weeks ago, Slashdot featured a cheap platform performing 80FFTs per second to recognize whistles. The platform is open hardware/open source and is aimed for sound processing projects. To this goal, the creator (limpkin) just implemented a simple proof of concept algorithm that will control your lighting once the platform listens to a particular word. A small video has been made to explain the basic concepts of sound recognition to encourage hobbyist to make their own."

1 of 30 comments (clear)

  1. Re: Not A Criticism, But... So What? by Anonymous Coward · · Score: 2, Informative

    If you can't see why this has more potential, you know nothing about DSP. Yes, for voice, 3 well-chosen fixed bands is mostly enough. But for whistling (as per the original application) or various other sounds, those same three bands will be pretty crap.

    Now we could make the 3 analog notch filters tunable via a DAC output, and get good results for one group (at a time) of a wide range of sounds, but that complicates it substantially. Yes, doing it with FFTs uses a lot more computational power -- but when the cheapest microcontrollers commonly used by hobbyists these days are a lot more powerful than the venerable Z80 (FYI, I built a single-board CP/M box back in the day), why in the world shouldn't we use some of that muscle to do more things, and some of it to do the same things better?