Search papers, labs, and topics across Lattice.
This paper introduces VoiceMem, a novel memory architecture designed for conversational systems, which integrates a parallel informational left brain and an emotional right brain to enhance real-time interaction. The architecture significantly improves accuracy in information retrieval and emotional personalization, outperforming traditional systems by nearly 30 points and achieving state-of-the-art results in persona modeling. Additionally, VoiceMem operates efficiently with a retrieval time of 134 ms, ensuring low latency and cost-effectiveness while maintaining high performance in real-world applications.
VoiceMem achieves a 30-point accuracy boost over traditional memory systems while delivering real-time, emotionally aware interactions without added latency.
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.
