For years, voice AI has been stuck in a rigid loop: think, then speak. But real human conversation is messy, overlapping, and asynchronous. …

For years, voice AI has been stuck in a rigid loop: think, then speak. But real human conversation is messy, overlapping, and asynchronous. In our new #ICASSP2026 work, we built a tandem architecture that shifts the paradigm to “speak while thinking.” A fast speech model starts replying instantly, while a backend LLM runs in parallel to inject deep knowledge on the fly. It’s a completely different way to approach conversational AI, making it feel remarkably more alive. Blog: https://pub.sakana.ai/kame/ 🐢 We’re excited to introduce KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI, accepted at #ICASSP2026! 🐢 Blog https://pub.sakana.ai/kame/ Paper https://arxiv.org/abs/2510.02327 Can a speech AI think deeply without pausing to proces…

Source: David Ha (X) | 2026-04-29