SOURCE-LINKED INTELLIGENCE

VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Conversational systems, such as duplex speech language models (SLMs), still lack a streaming, accurate, and empathetic memory system as their soul. We introduce VoiceMem, a simple memory architecture with a parallel informational left brain, an emotional right brain, and streaming memory I/O mechanisms. We further build a complete pipeline for memory-aware SLM training, long-horizon evaluation, and decoupled deployment with interchangeable memory backends. Experiments and real-world deployment show three advantages: i) Accuracy: under top-5 retrieval, the left brain outperforms classical syste

Read original source ↗ Open in workspace

recordType

paper

region

Global