VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Zhifei Xie →
“VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction”
- LinkedLinked via arxiv author · 85%Jiaqi Lang →
“VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction”
- LinkedLinked via arxiv author · 85%Ze An →
“VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction”
- LinkedLinked via arxiv author · 85%Yifan Zhao →
“VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction”
- LinkedLinked via arxiv author · 85%Dongchao Yang →
“VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction”
- LinkedLinked via arxiv author · 85%Yankai Lin →
“VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction”
- LinkedLinked via arxiv author · 85%Ziyang Ma →
“VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction”
- LinkedLinked via arxiv author · 85%Mingbao Lin →
“VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction”