3 papers
cs.SD2025
More Similar than Dissimilar: Modeling Annotators for Cross-Corpus Speech Emotion Recognition
James Tavernor, Emily Mower Provost
Speech emotion recognition systems often predict a consensus value generated from the ratings of multiple annotators. However, these models have limited ability to predict the anno…
eess.AS2025
The Whole Is Bigger Than the Sum of Its Parts: Modeling Individual Annotators to Capture Emotional Variability
James Tavernor, Yara El-Tawil, Emily Mower Provost
Emotion expression and perception are nuanced, complex, and highly subjective processes. When multiple annotators label emotional data, the resulting labels contain high variabilit…
cs.SD2025
Efficient Finetuning for Dimensional Speech Emotion Recognition in the Age of Transformers
Aneesha Sampath, James Tavernor, Emily Mower Provost
Accurate speech emotion recognition is essential for developing human-facing systems. Recent advancements have included finetuning large, pretrained transformer models like Wav2Vec…