SALMONN-duo: Adaptive Dual-System Coordination for Full-Duplex Voice Agents
Full-duplex speech large language models (LLMs) enable low-latency, natural voice interaction. However, real-world agents must also use tools and perform deliberative reasoning-operations whose variable latency and computational cost conflict with the stringent timing requirements of real-time conversation. To reconcil...
Wen-Yi Yu, Si-Yin Wang, T. Chiba et al.
· 0 citations