DPCRN: Dual-path Convolution Recurrent Network For Single Channel Speech Enhancement

Abstract

The dual-path RNN (DPRNN) was proposed to more effectively model extremely long sequences for speech separation in the time domain. By splitting long sequences to smaller chunks and applying intra-chunk and inter-chunk RNNs, the DPRNN reached promising performance in speech separation with a limited model size. In this paper, we combine the DPRNN module with Convolution Recurrent Network (CRN) and design a model called Dual-Path Convolution Recurrent Network (DPCRN) for speech enhancement in the time-frequency domain. We replace the RNNs in the CRN with DPRNN modules, where the intra-chunk RNNs are used to model the spectrum pattern in a single frame and the inter-chunk RNNs are used to model the dependence between consecutive frames. With only 0.8M parameters, the submitted DPCRN model achieves an overall mean opinion score (MOS) of 3.57 in the wide band scenario track of the Interspeech 2021 Deep Noise Suppression (DNS) challenge. Evaluations on some other test sets also show the eff

Stats

• citations81
• S2 citations—
• github stars0
• HF likes0
• heat score14.35
• arxiv keyle2021dpcrn

Related papers

• PDPCRN: Parallel Dual-path CRN With Bi-directional Inter-branch Interactions For Multi-channel Speech Enhancement (2023)0.00
• Dual-path RNN: Efficient Long Sequence Modeling For Time-domain Single-channel Speech Separation (2019)21.06
• DCCRN+: Channel-wise Subband DCCRN With SNR Estimation For Speech Enhancement (2021)0.00
• Multi-loss Convolutional Network With Time-frequency Attention For Speech Enhancement (2023)0.00
• DCCRN: Deep Complex Convolution Recurrent Network For Phase-aware Speech Enhancement (2020)20.78
• S-DCCRN: Super Wide Band DCCRN With Learnable Complex Feature For Speech Enhancement (2021)11.93
• Dual-path Self-attention RNN For Real-time Speech Enhancement (2020)0.00
• Inplace Gated Convolutional Recurrent Neural Network For Dual-channel Speech Enhancement (2021)0.00