Pre-trained Speech Processing Models Contain Human-Like Biases that Propagate to Speech Emotion Recognition

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.

Speech Emotion Recognition