---
title: "VoiceMem：流式双脑记忆架构，为实时语音交互提供记忆灵魂"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.26005v1"
permalink: "https://feed.astralor.com/items/itm_cb239a52103a3521857a3364"
published: "2026-08-26T16:50:05.000Z"
score: 78
channel: "ai"
tags: ["arXiv","VoiceMem","双工语音模型","实时语音交互","情感计算","记忆架构"]
---

# VoiceMem：流式双脑记忆架构，为实时语音交互提供记忆灵魂

## AI 点评

> 这篇论文最值得关注的是他们把记忆拆成“信息”和“情绪”两个通道，并且真的做到了实时级延迟。对做语音助手或Agent记忆层的技术人员，这套双脑架构和可插拔设计很有借鉴价值。另外134ms这个数字，说明记忆检索不再是语音交互的瓶颈了，产品上可以放开手脚。

## 速览

arXiv 最新论文提出 VoiceMem，一种专为双工语音语言模型（SLM）设计的流式记忆架构。它采用并行的“左脑”信息记忆与“右脑”情感记忆，配合流式记忆读写机制，并构建了完整的记忆感知SLM训练、长时评估和可解耦部署流水线。实验显示，其检索准确率（top-5）比经典系统Mem0（top-200）高出近30分；右脑在三个人格基准上达到SOTA，综合分提升4.29；检索延迟仅134ms，不增加额外对话延迟。VoiceMem为实时、个性化、有情感意识的语音交互提供了实用记忆底座。

## 关键点

- VoiceMem采用双脑架构：左脑负责信息记忆，右脑负责情感记忆，实现并行流式处理。
- 检索性能显著：top-5 检索比 Mem0 的 top-200 高出近30个百分点，延迟仅134ms。
- 情感与个性建模：右脑结合长短时情感归因和双节点人格建模，在3个基准上达到SOTA。
- 支持可插拔记忆后端，便于解耦部署，提供了从训练到评估的完整开源流水线。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_cb239a52103a3521857a3364