Study examines how audio LLMs handle conflicting speech and emotion cues
A new arXiv paper proposes an incongruence-aware evaluation of multimodal speech emotion recognition in audio large language models, testing how models respond when spoken content and vocal tone disagree.
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-11-02 05:00 · arXiv cs.AI
Incongruence-Aware Evaluation of Multimodal Speech Emotion Recognition in Audio Large Language Models