Evaluating Prompt Robustness in Text-to-Audio Systems for Adaptive Virtual Agents and Game Soundtracks

Abstract:Recent text-to-audio models enable adaptive game soundtracks, but small prompt changes can cause abrupt musical shifts. We evaluate MusicGen-small, MusicGen-large, and Stable Audio 2.5 under Minimal Lexical Substitution, Intensity Shifts, and Structural Rephrasing using log-Mel distance, MFCC/chroma-DTW, and CLAP similarity. Stable Audio 2.5 achieves the lowest pooled acoustic distances and the highest audio-audio CLAP similarity under structural rephrasing, while MusicGen-large has the highest audio-audio CLAP similarity under lexical substitutions and intensity shifts. Stable Audio 2.5 also shows the greatest between-seed variation in prompt-to-audio alignment, demonstrating the importance of multi-seed robustness evaluation for adaptive game audio.

4 pages, 2 figures. Poster paper published in the Proceedings of the ACM International Conference on Intelligent Virtual Agents (IVA 2026)

Sound (cs.SD); Artificial Intelligence (cs.AI)

arXiv:2603.13824 [cs.SD]

(or arXiv:2603.13824v3 [cs.SD] for this version)

https://doi.org/10.48550/arXiv.2603.13824 Focus to learn more arXiv-issued DOI via DataCite

Proc. ACM International Conference on Intelligent Virtual Agents (IVA 2026), ACM, 2026

https://doi.org/10.1145/3806774.3832791 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.