DeepAI AI Chat
Log In Sign Up

DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement

by   Xiaohuai Le, et al.
Nanjing University

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 efficacy of our model.


page 1

page 2

page 3

page 4


Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation

Recent studies in deep learning-based speech separation have proven the ...

Dual-path Self-Attention RNN for Real-Time Speech Enhancement

We propose a dual-path self-attention recurrent neural network (DP-SARNN...

DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement

Speech enhancement has benefited from the success of deep learning in te...

DPT-FSNet:Dual-path Transformer Based Full-band and Sub-band Fusion Network for Speech Enhancement

Recently, dual-path networks have achieved promising performance due to ...

TPARN: Triple-path Attentive Recurrent Network for Time-domain Multichannel Speech Enhancement

In this work, we propose a new model called triple-path attentive recurr...

TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids

Modern speech enhancement algorithms achieve remarkable noise suppressio...

TaylorAECNet: A Taylor Style Neural Network for Full-Band Echo Cancellation

This paper describes aecX team's entry to the ICASSP 2023 acoustic echo ...