45 citations · 59 across the 6 of their papers we have counts for
6 papers
KS-Net: Multi-band joint speech restoration and enhancement network for 2024 ICASSP SSI Challenge
Guochen Yu, Runqiang Han, Chenglin Xu +7
This paper presents the speech restoration and enhancement system created by the 1024K team for the ICASSP 2024 Speech Signal Improvement (SSI) Challenge. Our system consists of a…
BAE-Net: A Low complexity and high fidelity Bandwidth-Adaptive neural network for speech super-resolution
Guochen Yu, Xiguang Zheng, Nan Li +6
Speech bandwidth extension (BWE) has demonstrated promising performance in enhancing the perceptual speech quality in real communication systems. Most existing BWE researches prima…
RAMP: Retrieval-Augmented MOS Prediction via Confidence-based Dynamic Weighting
Hui Wang, Shiwan Zhao, Xiguang Zheng +1
Automatic Mean Opinion Score (MOS) prediction is crucial to evaluate the perceptual quality of the synthetic speech. While recent approaches using pre-trained self-supervised learn…
Multi-scale temporal-frequency attention for music source separation
Lianwu Chen, Xiguang Zheng, Chen Zhang +2
In recent years, deep neural networks (DNNs) based approaches have achieved the start-of-the-art performance for music source separation (MSS). Although previous methods have addre…
L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment
Eric Guizzo, Christian Marinoni, Marco Pennese +6
The L3DAS22 Challenge is aimed at encouraging the development of machine learning strategies for 3D speech enhancement and 3D sound localization and detection in office-like enviro…
A two-step backward compatible fullband speech enhancement system
Xu Zhang, Lianwu Chen, Xiguang Zheng +4
Speech enhancement methods based on deep learning have surpassed traditional methods. While many of these new approaches are operating on the wideband (16kHz) sample rate, a new fu…