English

LSZone: A Lightweight Spatial Information Modeling Architecture for Real-time In-car Multi-zone Speech Separation

Sound 2025-10-14 v1 Artificial Intelligence

Abstract

In-car multi-zone speech separation, which captures voices from different speech zones, plays a crucial role in human-vehicle interaction. Although previous SpatialNet has achieved notable results, its high computational cost still hinders real-time applications in vehicles. To this end, this paper proposes LSZone, a lightweight spatial information modeling architecture for real-time in-car multi-zone speech separation. We design a spatial information extraction-compression (SpaIEC) module that combines Mel spectrogram and Interaural Phase Difference (IPD) to reduce computational burden while maintaining performance. Additionally, to efficiently model spatial information, we introduce an extremely lightweight Conv-GRU crossband-narrowband processing (CNP) module. Experimental results demonstrate that LSZone, with a complexity of 0.56G MACs and a real-time factor (RTF) of 0.37, delivers impressive performance in complex noise and multi-speaker scenarios.

Keywords

Cite

@article{arxiv.2510.10687,
  title  = {LSZone: A Lightweight Spatial Information Modeling Architecture for Real-time In-car Multi-zone Speech Separation},
  author = {Jun Chen and Shichao Hu and Jiuxin Lin and Wenjie Li and Zihan Zhang and Xingchen Li and JinJiang Liu and Longshuai Xiao and Chao Weng and Lei Xie and Zhiyong Wu},
  journal= {arXiv preprint arXiv:2510.10687},
  year   = {2025}
}

Comments

submitted to ICASSP 2026

R2 v1 2026-07-01T06:32:27.298Z