Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.10687 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908589010976768 |
|---|---|
| author | Chen, Jun Hu, Shichao Lin, Jiuxin Li, Wenjie Zhang, Zihan Li, Xingchen Liu, JinJiang Xiao, Longshuai Weng, Chao Xie, Lei Wu, Zhiyong |
| author_facet | Chen, Jun Hu, Shichao Lin, Jiuxin Li, Wenjie Zhang, Zihan Li, Xingchen Liu, JinJiang Xiao, Longshuai Weng, Chao Xie, Lei Wu, Zhiyong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10687 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LSZone: A Lightweight Spatial Information Modeling Architecture for Real-time In-car Multi-zone Speech Separation Chen, Jun Hu, Shichao Lin, Jiuxin Li, Wenjie Zhang, Zihan Li, Xingchen Liu, JinJiang Xiao, Longshuai Weng, Chao Xie, Lei Wu, Zhiyong Sound Artificial Intelligence 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. |
| title | LSZone: A Lightweight Spatial Information Modeling Architecture for Real-time In-car Multi-zone Speech Separation |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2510.10687 |