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

Abstract

Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum, via a naive convolution neural network (CNN) or recurrent neural network (RNN). Some recent studies use complex-valued spectrogram as a training target but train in a real-valued network, predicting the magnitude and phase component or real and imaginary part, respectively. Particularly, convolution recurrent network (CRN) integrates a convolutional encoder-decoder (CED) structure and long short-term memory (LSTM), which has been proven to be helpful for complex targets. In order to train the complex target more effectively, in this paper, we design a new network structure simulating the complex-valued operation, called Deep Complex Convolution Recurrent Network (DCCRN), where both CNN and RNN structures can handle complex-valued operation. The proposed DCCRN models are very competitive over other previous networks, either on objective or subjective metric. With only 3.7M parameters, our DCCRN models submitted to the Interspeech 2020 Deep Noise Suppression (DNS) challenge ranked first for the real-time-track and second for the non-real-time track in terms of Mean Opinion Score (MOS).

Accepted by Interspeech 2020

References in corpus (4)

• End-to-End Multi-Channel Speech Separation
• Phase-aware Speech Enhancement with Deep Complex U-Net
• PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network
• A Unified Framework for Speech Separation

Cited by in corpus (12)

• Stochastic Restoration of Heavily Compressed Musical Audio using Generative Adversarial Networks
• VoiceFixer: Toward General Speech Restoration with Neural Vocoder
• CycleGAN-based Non-parallel Speech Enhancement with an Adaptive Attention-in-attention Mechanism
• Low-latency Monaural Speech Enhancement with Deep Filter-bank Equalizer
• Complex Spectral Mapping With Attention Based Convolution Recurrent Neural Network for Speech Enhancement
• Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
• Joint Echo Cancellation and Noise Suppression based on Cascaded Magnitude and Complex Mask Estimation
• Transformers with Competitive Ensembles of Independent Mechanisms
• DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement
• A Two-stage Complex Network using Cycle-consistent Generative Adversarial Networks for Speech Enhancement
• Ultra-Lightweight Speech Separation via Group Communication
• Investigation of Practical Aspects of Single Channel Speech Separation for ASR