2 papers
cs.SD2026
Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability
Xiaoxu Zhu, Junhua Li, Aaron J. Li +2
Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bia…
cs.LG2024
Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining
Aaron J. Li, Robin Netzorg, Zhihan Cheng +2
In recent years, work has gone into developing deep interpretable methods for image classification that clearly attributes a model's output to specific features of the data. One su…