The Remaining Cocktail Party Problem

Despite years of voice-first products being on the market, the cocktail party problem remains.

Image for post
Image for post
Image of a Flaming Cocktail

A few years back, I was sitting in a meeting with two lawyers. One of the lawyers was trying to dictate into a digital recorder a letter while the other was trying to add commentary. The first lawyer burst out “ONLY ONE OF US CAN TALK AT A TIME!”

Yesterday’s experience with my Echo Show reminded me of this. I was trying to ask Alexa to play a song, but there was a gaggle of people speaking. It was frustrating to be rejected all the time by Alexa on trigger. I had to walk up close to the device to get it to work properly. Ugh.

Despite years of the Echo being on the market (and Google Home), it seems, at least in some form factors, the cocktail party problem remains elusive. Maybe it’s not as big an issue in the field as it is a technical challenge for bragging rights among ambitious engineers. However, in some circumstances, it does make for frustrating interactions.

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