Improved Endpoint Detection

Image for post
Image for post

On reviewing some of commands placed to Alexa, I’m hearing that the endpoint detection is getting very good. Alexa isn’t tripped up by background noise or even other people speaking over the speaker.

Poor endpoint detection can make for a fickle interaction. We had issues in the past, and even with early AVS integrations, where the endpoint would linger and hit the timeout. This was usually the case in loud environments.

About a year back, Amazon started to require cloud wake word verification for the trigger (you had to send the audio that captured the wake word and it would be verified in the cloud).The same technology was likely used to improve the endpoint detection.

The result? Today, the Echo performs much better in noise and when there are multiple speakers.

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