A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditions
On the map: Speech and audio language models → Speech enhancement and noise suppression
Abstract (arXiv)
Although deep learning based multi-channel speech enhancement has achieved significant advancements, its practical deployment is often limited by constrained computational resources, particularly in low signal-to-noise ratio (SNR) conditions. In this paper, we propose a lightweight hybrid dual-channel speech enhancement system that combines independent vector analysis (IVA) with a modified version of the dual-channel grouped temporal convolutional recurrent network (GTCRN). IVA functions as a coarse estimator, providing auxiliary information for both speech and noise, while the modified GTCRN further refines the speech quality. We investigate several modifications to ensure the comprehensive utilization of both original and auxiliary information. Experimental results demonstrate the effectiveness of the proposed system, achieving enhanced speech with minimal parameters and low computational complexity.
Key facts. Cited by 1 paper in the map (data through 19 Oct 2026). Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models. Builds on 14 of its 29 references that are in the map. First posted on arXiv 26 May 2025.
Builds on
14 of 29 references.
Closest ancestors · 3
Same direction, newest first
- 2024SNR-Progressive Model with Harmonic Compensation for Low-SNR Speech Enhancement24 Jun
- 2023Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model1 Jun
- 2021DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement12 Jul
Other references · 11
- 2014Adam: A Method for Stochastic Optimizationcited by 38,210
- 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,143
- 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 356
- 2019Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separationcited by 275
- 2017A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancementcited by 67
- 2020ICASSP 2021 Deep Noise Suppression Challengecited by 57
- 2018Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Modelcited by 47
- 2020A consolidated view of loss functions for supervised deep learning-based speech enhancementcited by 43
- 2020ADL-MVDR: All deep learning MVDR beamformer for target speech separationcited by 40
- 2022Description and Discussion on DCASE 2022 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Applying Domain Generalization Techniquescited by 21
- 2020UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-noise Ratio Conditioncited by 9
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2021Multi-channel Speech Enhancement with 2-D Convolutional Time-frequency Domain Features and a Pre-trained Acoustic Model
- 2021Inplace Gated Convolutional Recurrent Neural Network For Dual-channel Speech Enhancement
- 2025Hybrid Real- and Complex-Valued Neural Network Architecture for Speech Enhancement
- 2021Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions
- 2024Improving Speech Enhancement by Integrating Inter-Channel and Band Features with Dual-branch Conformer
- 2022On the Role of Spatial, Spectral, and Temporal Processing for DNN-based Non-linear Multi-channel Speech Enhancement
- 2021Inter-channel Conv-TasNet for multichannel speech enhancement
- 2023PCNN: A Lightweight Parallel Conformer Neural Network for Efficient Monaural Speech Enhancement