Acoustic Echo Cancellation

Image for post
Image for post

One of the more magical experiences with a voice interactive device is the ability to interrupt it while it’s speaking or playing music. One way this is done is referred to as acoustic echo cancellation. The line out from the device is fed back into a digital signal processing algorithm that tries to remove a similar signal from the input.

The result is that despite loud music coming from a device, the input line sounds dead quiet, meaning users can still interact with the device by voice. The first time I used this type of processing with a variant of the Ubi, the results were stunning. Music could be blaring out of the speakers but you could still get an accurate result from the device at 7 feet away.

Here’s a demo:

While this demo would be impractical to implement using the same hardware (the Acoustic Magic microphone is about $400 USD), it shows what is possible (and this is well over a year ago). Now, in DSP form, similar technology is in the sub-$10 range.

This means we’ll be getting a lot more reliable voice interaction in the year ahead.

Written by

Independent daily thoughts on all things future, voice technologies and AI. More at

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store