Who’s Who of Speaker Differentiation

Image for post
Image for post
Convolution Autoencoder from Towards Data Science.

It was amazing to see Daniel Shapiro, PhD present last week at ISCEE 2018 in Eilat. Daniel recently posted about his talk at the conference and he goes over the research very well.

I’ll write more about this but speaker separation (or differentiation) is part of a bigger problem to identify who’s speaking. This is also referred to as the cocktail party problem. We’re able to tune out others who are speaking but machines have a difficult time doing this. Resource intensive strategies include beam forming DSPs or blind source separation.

With this paper, the team came up with a very low power method of figuring out who’s who from mixed audio.

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