BP-CRN: A Lightweight Two-Stage Convolutional Recurrent Network for Multi-Channel Speech Enhancement

• Published in: IEICE Transactions on Information and Systems Vol. E108.D; no. 2; pp. 161 - 164
• Main Authors: ZHAO, Li, CHENG, Jiaming, ZHOU, Lin, PANG, Cong, NI, Ye
• Format: Journal Article
• Language: English
• Published: Tokyo The Institute of Electronics, Information and Communication Engineers 01.02.2025; Japan Science and Technology Agency
• Subjects: Beamforming; complex network; convolutional recurrent network; Encoding-Decoding; lightweight; Modules; multichannel speech enhancement; neural beamforming; Spatial data; Spatial filtering; Speech processing
• ISSN: 0916-8532; 1745-1361
• DOI: 10.1587/transinf.2024EDL8042

In our work, we propose a lightweight two-stage convolutional recurrent network (BP-CRN) for multichannel speech enhancement (mcse), which consists of beamforming and post-filtering. Drawing inspiration from traditional methods, we design two core modules for spatial filtering and post-filtering with compensation, named BM and PF, respectively. Both core modules employ a convolutional encoding-decoding structure and utilize complex frequency-time long short-term memory (CFT-LSTM) blocks in the middle. Furthermore, the inter-module mask module is introduced to estimate and convey implicit spatial information and assist the post-filtering module in refining spatial filtering and suppressing residual noise. Experimental results demonstrate that, our proposed method contains only 1.27M parameters and outperforms three other mcse methods in terms of PESQ and STOI metrics.