Style Amnesia in Spoken Language Models
Published:Dec 29, 2025 16:23
•1 min read
•ArXiv
Analysis
This paper addresses a critical limitation in spoken language models (SLMs): the inability to maintain a consistent speaking style across multiple turns of a conversation. This 'style amnesia' hinders the development of more natural and engaging conversational AI. The research is important because it highlights a practical problem in current SLMs and explores potential mitigation strategies.
Key Takeaways
- •SLMs suffer from 'style amnesia,' failing to maintain speaking styles across multiple turns.
- •Explicitly asking the model to recall the style instruction can partially mitigate the issue.
- •SLMs perform poorly when style instructions are placed in system prompts.
- •The research focuses on paralinguistic speaking styles like emotion, accent, volume, and speaking speed.
Reference
“SLMs struggle to follow the required style when the instruction is placed in system messages rather than user messages, which contradicts the intended function of system prompts.”