This page requires Javascript. Please enable it to view the website. Two Heads Are Better Than One: Async Knowledge Injection for Speech AI with Tandem Architecture We're excited to introduce KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI. KAME means turtle in Japanese. Paper (arxiv): https://arxiv.org/abs/2510.02327 (Accepted at ICASSP 2026) Infe

