BT Start of Speech Delay

Image for post
Image for post

There’s still a very clunky experience when it comes to dictating text messages in a car through an Android device that is using BT to output audio. This is from the buffer delay in BT output.

Playing music and podcasts, this isn’t such a big deal because it only happens at the start of streaming. It can lead to a double input but that’s only when one is really impatient (actually making it more frustrating).

However, one of places where it introduces a lot of issues is with voice interaction. Especially if one doesn’t want to be distracted with a touch input while driving, listening for the start of speech indication is crucial.

The issue with BT paired devices is that for voice interaction, the mic might have already started listening by the time the audio acknowledgement plays through the speaker. This can lead to at least two issues:

  1. The acknowledgement beep affects the processing algorithms by setting things like active gain control (adjusting microphone levels) or creating a noise source that competes with the user’s speech.
  2. Causing an early end point detection.

Perhaps newer version of BT will address this (or in my ignorance, already have).

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