Lin Zhou^1,*, Xijin Chen¹, Chaoyan Wu¹, Qiuyue Zhong¹, Xu Cheng², Yibin Tang³

CMC-Computers, Materials & Continua, Vol.74, No.1, pp. 1259-1277, 2023, DOI:10.32604/cmc.2023.027379

Abstract Masking-based and spectrum mapping-based methods are the two main algorithms of speech enhancement with deep neural network (DNN). But the mapping-based methods only utilizes the phase of noisy speech, which limits the upper bound of speech enhancement performance. Masking-based methods need to accurately estimate the masking which is still the key problem. Combining the advantages of above two types of methods, this paper proposes the speech enhancement algorithm MM-RDN (masking-mapping residual dense network) based on masking-mapping (MM) and residual dense network (RDN). Using the logarithmic power spectrogram (LPS) of consecutive frames, MM estimates the ideal ratio masking (IRM) matrix of… More >

Lin Zhou^1,*, Qiuyue Zhong¹, Tianyi Wang¹, Siyuan Lu¹, Hongmei Hu²

Computer Systems Science and Engineering, Vol.38, No.3, pp. 279-289, 2021, DOI:10.32604/csse.2021.016524

Abstract Generative adversarial networks (GANs) are paid more attention to dealing with the end-to-end speech enhancement in recent years. Various GAN-based enhancement methods are presented to improve the quality of reconstructed speech. However, the performance of these GAN-based methods is worse than those of masking-based methods. To tackle this problem, we propose speech enhancement method with a residual dense generative adversarial network (RDGAN) contributing to map the log-power spectrum (LPS) of degraded speech to the clean one. In detail, a residual dense block (RDB) architecture is designed to better estimate the LPS of clean speech, which can extract rich local features… More >