Enrolment-based personalisation for improving individual-level fairness in speech emotion recognition
A Triantafyllopoulos, B Schuller - arXiv preprint arXiv:2406.06665, 2024 - arxiv.org
The expression of emotion is highly individualistic. However, contemporary speech emotion
recognition (SER) systems typically rely on population-level models that adopt aone-size-fits …
recognition (SER) systems typically rely on population-level models that adopt aone-size-fits …
[PDF][PDF] Analysis and automatic prediction of exertion from speech: Contrasting objective and subjective measures collected while running
Monitoring runner exertion in real-time can provide unique insights that help improve
training and reduce injuries. Most existing methods use heart rate (HR) as a physiological …
training and reduce injuries. Most existing methods use heart rate (HR) as a physiological …