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.
Blogger's Review: This paper provides an in-depth exploration of the safety measures for speech assistants in automotive applications, highlighting the limitations of current technologies in real-world scenarios. The issues of latency and uncertainty serve as a reminder that we must balance user experience and system reliability when advancing technological applications. While current implementations are inadequate, they also pave the way for future improvements and innovations.