no code implementations • 8 Apr 2022 • Yehoshua Dissen, Felix Kreuk, Joseph Keshet
Specifically, the study focuses on generating high-quality neural speaker representations without any annotated data, as well as on estimating secondary hyperparameters of the model without annotations.
no code implementations • 6 Nov 2016 • Yehoshua Dissen, Joseph Keshet, Jacob Goldberger, Cynthia Clopper
We then freeze the parameters of the trained network and use several different datasets to train an adaptation layer that makes the obtained network universal in the sense that it works well for a variety of speakers and speech domains with very different characteristics.