Effcrn: An Efficient Convolutional Recurrent Network For High-performance Speech Enhancement

Abstract

Fully convolutional recurrent neural networks (FCRNs) have shown state-of-the-art performance in single-channel speech enhancement. However, the number of parameters and the FLOPs/second of the original FCRN are restrictively high. A further important class of efficient networks is the CRUSE topology, serving as reference in our work. By applying a number of topological changes at once, we propose both an efficient FCRN (FCRN15), and a new family of efficient convolutional recurrent neural networks (EffCRN23, EffCRN23lite). We show that our FCRN15 (875K parameters) and EffCRN23lite (396K) outperform the already efficient CRUSE5 (85M) and CRUSE4 (7.2M) networks, respectively, w.r.t. PESQ, DNSMOS and DeltaSNR, while requiring about 94% less parameters and about 20% less \#FLOPs/frame. Thereby, according to these metrics, the FCRN/EffCRN class of networks provides new best-in-class network topologies for speech enhancement.

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keysach2023effcrn

Related papers

• Wavecrn: An Efficient Convolutional Recurrent Neural Network For End-to-end Speech Enhancement (2020)14.02
• Deep Residual Echo Suppression And Noise Reduction: A Multi-input FCRN Approach In A Hybrid Speech Enhancement System (2021)8.09
• Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks (2020)5.84
• Complex Spectral Mapping With Attention Based Convolution Recurrent Neural Network For Speech Enhancement (2021)0.00
• FRCRN: Boosting Feature Representation Using Frequency Recurrence For Monaural Speech Enhancement (2022)22.16
• DPCRN: Dual-path Convolution Recurrent Network For Single Channel Speech Enhancement (2021)14.35
• TFCN: Temporal-frequential Convolutional Network For Single-channel Speech Enhancement (2022)0.00
• DCCRN: Deep Complex Convolution Recurrent Network For Phase-aware Speech Enhancement (2020)20.78