This was fantastic! How many samples were thrown at the mics? Would be great to know what baseline WER was if audio was fed directly to the API. Benchmarking is critical for knowing which technology will actually perform best. One thing we’ve seen from our experience is that linear array mics (e.g. PS3 Eye) tend to perform better than circular arrays when the angle of arrival is known and within 180 degrees. Would love to see more of this!

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