Altered Spontaneous Brain Activity Patterns of Meibomian Gland Dysfunction in Severely Obese Population Measured Using the Fractional Amplitude of Low-Frequency Fluctuations

Xu, Yuling; Wang, Xiaoyu; Kang, Min; Wang, Yixin; Zhang, Lijuan; Shu, Hui‐Ye; Liao, Xu‐Lin; Zou, Jie; Wei, Hong; Ling, Qian; Shao, Yi

doi:10.3389/fpsyt.2022.914039

Cited by 2 publications

(1 citation statement)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To collect the raw data, we collected examination report descriptions and doctor diagnoses, which are key clinical records, generated by three imaging devices: OSA [40], CFP [41], and OCT [42,43]. Specifically, during the data collection process, each patient's examination report for each imaging modality was treated as a sample.…”

Section: ) Data Cleaningmentioning

confidence: 99%

Infectious Hospital Area, the First Affiliated Hospital of University of Science and Technology of China, Hefei, China

Zhao¹,

Hu²,

Xue³

et al. 2021

BEBM

View full text Add to dashboard Cite

With advances in deep learning, neural network based speech enhancement (SE) has developed rapidly in the last decade. Meanwhile, the self-supervised pre-trained model and vector quantization (VQ) have achieved excellent performance on many speech-related tasks, while they are less explored on SE. As it was shown in our previous work that utilizing a VQ module to discretize noisy speech representations is beneficial for speech denoising, in this work we therefore study the impact of using VQ at different layers with different number of codebooks. Different VQ modules indeed enable to extract multiplegranularity speech features. Following an attention mechanism, the contextual features extracted by a pre-trained model are fused with the local features extracted by the encoder, such that both global and local information are preserved to reconstruct the enhanced speech. Experimental results on the Valentini dataset show that the proposed model can improve the SE performance, where the impact of choosing pre-trained models is also revealed.

show abstract