CST-UNet: Cross Swin Transformer Enhanced U-Net with Masked Bottleneck for Single-Channel Speech Enhancement

Zipeng Zhang; Wei Chen; Weiwei Guo; Yiming Liu; Jianhua Yang; Houguang Liu

doi:10.1007/s00034-024-02736-9

ScienceGate Book Chapters

JOURNAL ARTICLE

CST-UNet: Cross Swin Transformer Enhanced U-Net with Masked Bottleneck for Single-Channel Speech Enhancement

Zipeng Zhang Wei Chen Weiwei Guo Yiming Liu Jianhua Yang Houguang Liu

Year: 2024 Journal: Circuits Systems and Signal Processing Vol: 43 (9)Pages: 5989-6010 Publisher: Birkhäuser

DOI: 10.1007/s00034-024-02736-9

Get Full-Text PDF Get Analytical Report

Keywords:

Bottleneck Computer science PESQ Encoder Computational complexity theory Transformer Computation Redundancy (engineering) Deep learning Speech recognition Computer engineering Artificial intelligence Speech enhancement Pattern recognition (psychology) Algorithm Embedded system Engineering Noise reduction

Metrics

Cited By

1.43

FWCI (Field Weighted Citation Impact)

Refs

0.70

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Speech and Audio Processing

Physical Sciences → Computer Science → Signal Processing

Speech Recognition and Synthesis

Physical Sciences → Computer Science → Artificial Intelligence

Advanced Adaptive Filtering Techniques

Physical Sciences → Engineering → Computational Mechanics

CST-UNet: Cross Swin Transformer Enhanced U-Net with Masked Bottleneck for Single-Channel Speech Enhancement

Metrics

Citation History

Topics

Related Documents

ST-Unet: Swin Transformer boosted U-Net with Cross-Layer Feature Enhancement for medical image segmentation

Swin-CasUNet: Cascaded U-Net with Swin Transformer for Masked Face Restoration

Masked Swin Transformer Unet for Industrial Anomaly Detection

Swin-BFB-UNet: a Swin transformer-based UNet combined with bottleneck fusion block for vertebra segmentation

ATNSCUNet: Adaptive Transformer Network based Sub-Convolutional U-Net for Single channel Speech Enhancement