Adaptive selection of local and non-local attention mechanisms for speech enhancement
In speech enhancement tasks, local and non-local attention mechanisms have been
significantly improved and well studied. However, a natural speech signal contains many …
significantly improved and well studied. However, a natural speech signal contains many …
CFNet: Automatic multi-modal brain tumor segmentation through hierarchical coarse-to-fine fusion and feature communication
Y Cheng, Y Zheng, J Wang - Biomedical Signal Processing and Control, 2025 - Elsevier
Automatic segmentation of brain tumors employing images from multi-modalities is important
for preoperative diagnosis and prognostic assessment. The rich complementary information …
for preoperative diagnosis and prognostic assessment. The rich complementary information …
DeConformer-SENet: An Efficient Deformable Conformer Speech Enhancement Network
M Li, Y Liu, L Zhou - Digital Signal Processing, 2024 - Elsevier
The Conformer model has demonstrated superior performance in speech enhancement by
combining the long-range relationship modeling capability of self-attention with the local …
combining the long-range relationship modeling capability of self-attention with the local …
Improving Speech Enhancement by Integrating Inter-Channel and Band Features with Dual-branch Conformer
J Li, X Xu, W Tu, Y Yang, R Zhu - arXiv preprint arXiv:2407.06524, 2024 - arxiv.org
Recent speech enhancement methods based on convolutional neural networks (CNNs) and
transformer have been demonstrated to efficaciously capture time-frequency (TF) …
transformer have been demonstrated to efficaciously capture time-frequency (TF) …
An Efficient and Interpre Table Speech Enhancement Network Via Deep Dictionary Learning
X Xu, Y Zhang, W Tu, Y Yang - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
Speech enhancement is a vital and highly ill-posed problem for many speech downstream
tasks. While currently existing deep learning based speech enhancement methods have …
tasks. While currently existing deep learning based speech enhancement methods have …
Curricular Contrastive Regularization for Speech Enhancement with Self-Supervised Representations
X Xu, C Han, Y Zhang, W Tu… - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
Existing deep learning-based speech enhancement methods only adopt clean speech as
positive samples to guide the training of speech enhancement networks while negative …
positive samples to guide the training of speech enhancement networks while negative …