SIGMA applies post-hoc XAI saliency maps to define reusable sparse masks for magnitude-bounded perturbations on self-supervised speech features, evaluated on IEMOCAP and TESS for competitive attack success with explanation consistency trade-offs.
Toronto emotional speech set (TESS),
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
An emotion prediction model using 3-layer CNN plus AFME algorithm on speech and image data detects seven basic emotions and sarcasm at 85-96% accuracy, addressing cultural challenges in Black African conversational AI.
citing papers explorer
-
SIGMA: Saliency-Guided Sparse Mask Attacks for Speech Emotion Recognition
SIGMA applies post-hoc XAI saliency maps to define reusable sparse masks for magnitude-bounded perturbations on self-supervised speech features, evaluated on IEMOCAP and TESS for competitive attack success with explanation consistency trade-offs.
-
Evaluation of Conversational Agents: Understanding Culture, Context and Environment in Emotion Detection
An emotion prediction model using 3-layer CNN plus AFME algorithm on speech and image data detects seven basic emotions and sarcasm at 85-96% accuracy, addressing cultural challenges in Black African conversational AI.