activity
20182021
most citedDenoising convolutional autoencoder based B-mode ultrasound tongue image feature extraction

4 citations · 4 across the 1 of their papers we have counts for

collaborators

6 papers

cs.LG2021

FedH2L: Federated Learning with Model and Statistical Heterogeneity

Yiying Li, Wei Zhou, Huaimin Wang +2

Federated learning (FL) enables distributed participants to collectively learn a strong global model without sacrificing their individual data privacy. Mainstream FL approaches req…

eess.IV20194 cited

Denoising convolutional autoencoder based B-mode ultrasound tongue image feature extraction

Bo Li, Kele Xu, Dawei Feng +3

B-mode ultrasound tongue imaging is widely used in the speech production field. However, efficient interpretation is in a great need for the tongue image sequences. Inspired by the…

cs.CV2018

General audio tagging with ensembling convolutional neural network and statistical features

Kele Xu, Boqing Zhu, Qiuqiang Kong +4

Audio tagging aims to infer descriptive labels from audio clips. Audio tagging is challenging due to the limited size of data and noisy labels. In this paper, we describe our solut…

cs.LG2018

Collaborative Deep Learning Across Multiple Data Centers

Kele Xu, Haibo Mi, Dawei Feng +4

Valuable training data is often owned by independent organizations and located in multiple data centers. Most deep learning approaches require to centralize the multi-datacenter da…

cs.CV2018

Sample Dropout for Audio Scene Classification Using Multi-Scale Dense Connected Convolutional Neural Network

Dawei Feng, Kele Xu, Haibo Mi +2

Acoustic scene classification is an intricate problem for a machine. As an emerging field of research, deep Convolutional Neural Networks (CNN) achieve convincing results. In this…

cs.CV2018

Mixup-Based Acoustic Scene Classification Using Multi-Channel Convolutional Neural Network

Kele Xu, Dawei Feng, Haibo Mi +5

Audio scene classification, the problem of predicting class labels of audio scenes, has drawn lots of attention during the last several years. However, it remains challenging and f…