A Real-Time Speech Enhancement Algorithm Based on Convolutional Recurrent Network and Wiener Filter

Major breakthroughs have been made in speech enhancement with the introduction of deep learning. However, the noise reduction performance under the lower signal-to-noise ratio (SNR) conditions and the noise generalization ability of the model are still to be improved. In this paper, we propose a novel real-time monaural speech enhancement algorithm by combining the convolutional recurrent network (CRN) and Wiener filter. The CRN includes a convolutional encoder-decoder (CED) and a gated recurrent unit (GRU), and the Wiener filter gain function is optimized according to the output of the CRN. The proposed CRN-Wiener model adopts a causal system and achieves a high parameter efficiency, which results in a real-time speech enhancement system. The experimental results show that the proposed system obviously outperforms the baselines under the lower SNR conditions. Moreover, it achieves a stronger noise generalization performance for both the unmatched noises and the untrained SNRs.