In the first post I argued there are two ways to pull meaning out of audio: measure it with signal processing, or estimate it with a model. This post is the story of a problem where the obvious move was to estimate — and where measuring turned out to be better. The problem: labeling who is spea...
Source: [Dev.to](https://dev.to/dimastatz/measure-dont-estimate-labeling-speakers-without-a-gated-model-3pgm)