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

2026-08-26

AI Summary

论文提出VoiceMem，一种具有信息和情感双脑结构的记忆架构，用于提高对话系统的准确性、个性化及实时性。

Abstract

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 systems such as Mem0 at top-200 by nearly 30 points; ii) Emotional & Personal: the right brain, with short- and long-horizon affective attribution and dual-node persona modeling, achieves state-of-the-art performance across three persona benchmarks and improves the aggregate score by 4.29 points over the previous best system; and iii) Real-Time & Cheap: VoiceMem completes retrieval in 134 ms, well within standard VAD latency, adding no extra conversational delay while maintaining high accuracy and low cost. These results show that VoiceMem provides a practical memory foundation for real-time, personalized, and emotionally aware speech interaction.

Problem

• conversational systems
• memory system
• real-time interaction

Innovation

• Streaming Memory
• Dual-Brain Architecture
• Real-Time Interaction
• Affective Attribution
• Persona Modeling