Spoken Function Calling: A New Perspective on Spoken Language Understanding for Large Audio Language Models

Yuezhang Peng, Yuxin Liu, Changfeng Gao, Zhifu Gao, Xiangang Li et al.|August 5, 2026arXiv

Key Takeaway

Framing spoken language understanding as structured function calling—rather than slot-filling—lets audio language models generalize to new tasks without retraining, similar to how code models handle function calls.

Summary

This paper introduces Spoken Function Calling (SFC), a new way to understand spoken language that treats semantic extraction like function calls with structured definitions.

multimodal applications training

Key Terms

spoken-language-understanding in-context-learning audio-language-model function-calling post-training