Speech Large Language Models (LLMs) show great promise for speech emotion recognition (SER) via generative interfaces. However, shifting from closed-set classification to open text generation introduces zero-shot stochasticity, making evaluation highly sensitive to prompts. Additionally, conventional speech LLMs benchmarks overlook the inherent ambiguity of human emotion. Hence, we present VoxEmo, a comprehensive SER benchmark encompassing 35 emotion corpora across 15 languages for Speech LLMs. VoxEmo provides a standardized toolkit featuring varying prompt complexities, from direct classification to paralinguistic reasoning. To reflect real-world perception/application, we introduce a distribution-aware soft-label protocol and a prompt-ensemble strategy that emulates annotator disagreement. Experiments reveal that while zero-shot speech LLMs trail supervised baselines in hard-label accuracy, they uniquely align with human subjective distributions.
@article{arxiv.2603.08936,
title = {VoxEmo: Benchmarking Speech Emotion Recognition with Speech LLMs},
author = {Hezhao Zhang and Huang-Cheng Chou and Shrikanth Narayanan and Thomas Hain},
journal= {arXiv preprint arXiv:2603.08936},
year = {2026}
}