Bajian Xiang

Bajian Xiang

Auto-generated profile, based on publicly available information

Bajian Xiang

Laboratory of High-speed Circuit and Artificial Neural Networks, Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 January 2024 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
BXBajian Xiang
Bajian Xiang
WMWenyu Mao
Wenyu Mao
KTKaijun Tan
Kaijun Tan
HLHuaxiang Lu
Huaxiang Lu
Reverberation significantly degrades speech intelligibility, posing a substantial challenge in speech processing. While deep learning advancements offer promising solutions, current methodologies often overlook the effective integration of low-level and high-level feature representations, causing detrimental effects on overall performance. Simultaneously, prior approaches heavily rely on loss functions grounded in quantitative error metrics, which may not fully capture the perceptual intricacies of speech signals. To address these concerns, we introduce CAT-DUnet, a Unet architecture that integrates channel attention, time-frequency attention, and dilated convolution blocks to enhance feature fusion. We innovatively leverage the structural similarity as the training objective to align more closely with human perception, and investigate the effect of applying various reasonable transformations to spectrograms on the performance of the loss function. Through extensive ablation experiments, we demonstrate the effectiveness of our proposed enhancements. Our model outperforms state-of-the-art models on 6 out of 7 metrics, underscoring its exceptional performance.