TY - JOUR
T1 - A neural network approach for speech enhancement and noise-robust bandwidth extension
AU - Hao, Xiang
AU - Xu, Chenglin
AU - Zhang, Chen
AU - Xie, Lei
N1 - Publisher Copyright:
© 2024 Elsevier Ltd
PY - 2025/1
Y1 - 2025/1
N2 - When processing noisy utterances with varying frequency bandwidths using an enhancement model, the effective bandwidth of the resulting enhanced speech often remains unchanged. However, high-frequency components are crucial for perceived audio quality, underscoring the need for noise-robust bandwidth extension capabilities in speech enhancement networks. In this study, we addressed this challenge by proposing a novel network architecture and loss function based on the CAUNet, which is a state-of-the-art speech enhancement method. We introduced a multi-scale loss and implemented a coordinate embedded upsampling block to facilitate bandwidth extension while maintaining the ability of speech enhancement. Additionally, we proposed a gradient loss function to promote the neural network's convergence, leading to significant performance improvements. Our experimental results validate these modifications and clearly demonstrate the superiority of our approach over competing methods.
AB - When processing noisy utterances with varying frequency bandwidths using an enhancement model, the effective bandwidth of the resulting enhanced speech often remains unchanged. However, high-frequency components are crucial for perceived audio quality, underscoring the need for noise-robust bandwidth extension capabilities in speech enhancement networks. In this study, we addressed this challenge by proposing a novel network architecture and loss function based on the CAUNet, which is a state-of-the-art speech enhancement method. We introduced a multi-scale loss and implemented a coordinate embedded upsampling block to facilitate bandwidth extension while maintaining the ability of speech enhancement. Additionally, we proposed a gradient loss function to promote the neural network's convergence, leading to significant performance improvements. Our experimental results validate these modifications and clearly demonstrate the superiority of our approach over competing methods.
KW - Neural networks
KW - Speech bandwidth extension
KW - Speech enhancement
UR - http://www.scopus.com/inward/record.url?scp=85201257800&partnerID=8YFLogxK
U2 - 10.1016/j.csl.2024.101709
DO - 10.1016/j.csl.2024.101709
M3 - 文章
AN - SCOPUS:85201257800
SN - 0885-2308
VL - 89
JO - Computer Speech and Language
JF - Computer Speech and Language
M1 - 101709
ER -