Safeguards for Speech2Speech LLM-Assistants: A Case Study in Automotive Applications

Abstract:Recent advances have introduced speech-to-speech (S2S) conversational assistants capable of producing natural-sounding interactions, including non-verbal cues like tonality and mood. In the automotive domain, this enables intuitive and humanlike in-car dialogue experiences. However, integrating these end-to-end assistants limits architectural options for programmable domain-specific safeguards. This paper discusses two implementation approaches for S2S guardrails: transcript-based and tool-based. Through an empirical evaluation, we demonstrate that both strategies are insufficient for industrial deployment in most cases due to prohibitive latency (delaying each answer by 0 to 1.4 seconds even for computationally cheap checks) and technical impediments (like potentially non-deterministic tool call behavior). Finally, we outline open challenges for S2S guardrails in the automotive context.

Artificial Intelligence (cs.AI)

arXiv:2607.21180 [cs.AI]

(or arXiv:2607.21180v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2607.21180 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

https://doi.org/10.1007/978-3-032-32335-4_18 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.