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

By Yanxin Hu, Yun Liu, Shubo Lv, Mengtao Xing, Shimin Zhang, Yihui Fu, Jian Wu, Bihong Zhang, Lei Xie. 2020

804 citations recorded by the source corpus.

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).

Subfields: Artificial Intelligence, Mechanics of Materials, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jinyu Li
2. Dong Yu
3. Zhuo Chen
4. Li Deng
5. Takuya Yoshioka
6. Shujie Liu
7. Yu Wu
8. Sanyuan Chen

In Signal Processing

1. Jinyu Li
2. Dong Yu
3. Zhuo Chen
4. Li Deng
5. Takuya Yoshioka
6. Shujie Liu
7. Yu Wu
8. Sanyuan Chen

Citations in the corpus

• Complex Neural Spatial Filter: Enhancing Multi-Channel Target Speech Separation in Complex Domain (2021, methodology): “The complex BLSTM layer is implemented according to [24].”
• FB-MSTCN: A Full-Band Single-Channel Speech Enhancement Method Based on Multi-Scale Temporal Convolutional Network (2022, background): “In the first stage, the complex ratio masks (CRMs) [1] are estimated to initially en-1 hance the noisy signal, and then the second-stage module can further compensate the enhanced complex signal.”
• Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement (2021, methodology): “For further details of DCCRN, we refer the reader to [3].”
• Investigation of Practical Aspects of Single Channel Speech Separation for ASR (2021, methodology): “The CRN structure is a real-valued version of the DCCRN [37], and consists of a 7-layer encoder/decoder with 3 layer bidirectional LSTMs.”
• FRCRN: Boosting Feature Representation Using Frequency Recurrence for Monaural Speech Enhancement (2022, positive): “We choose a CRN-based DCCRN [6] model and a two-stream network, PHASEN [15], as baselines.”
• Personalized speech enhancement: new models and Comprehensive evaluation (2021, methodology): “Our previous experiments [5] showed that DCCRN [4] achieved high-quality SE in terms of both ASR accuracy and perceptual quality.”
• FullSubNet+: Channel Attention Fullsubnet with Complex Spectrograms for Speech Enhancement (2022, methodology): “In addition to showing the effectiveness of the improvements for the FullSubNet, we compare FullSubNet+ with some current SOTA methods [22–26] in Table 1.”
• Fullsubnet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement (2020, methodology): “DCCRN [19] simulates the complex-valued operation inside the convolution recurrent network.”