1 code implementation • 29 Oct 2023 • Isaac Slaughter, Craig Greenberg, Reva Schwartz, Aylin Caliskan
We compare biases found in pre-trained models to biases in downstream models adapted to the task of Speech Emotion Recognition (SER) and find that in 66 of the 96 tests performed (69%), the group that is more associated with positive valence as indicated by the SpEAT also tends to be predicted as speaking with higher valence by the downstream model.
no code implementations • 14 Sep 2020 • Lydia P. Gleaves, Reva Schwartz, David A. Broniatowski
There is increased interest in assisting non-expert audiences to effectively interact with machine learning (ML) tools and understand the complex output such systems produce.