765 citations · 988 across the 38 of their papers we have counts for
9 papers · 1 filter
The RoyalFlush System for the WMT 2022 Efficiency Task
Bo Qin, Aixin Jia, Qiang Wang +4
This paper describes the submission of the RoyalFlush neural machine translation system for the WMT 2022 translation efficiency task. Unlike the commonly used autoregressive transl…
Effects of Disorder On Thouless Pumping In Higher-Order Topological Insulators
Congwei Lu, Zhao-Fan Cai, Haibo Wang +2
We investigate the effects of random onsite disorder on higher-order Thouless pumping of noninteracting fermionic Benalcazar-Bernevig-Hughes (BBH) model. The interplay of disorderi…
Pushing the limits of self-supervised speaker verification using regularized distillation framework
Yafeng Chen, Siqi Zheng, Hui Wang +2
Training robust speaker verification systems without speaker labels has long been a challenging task. Previous studies observed a large performance gap between self-supervised and…
Measurement of the Neutron Cross Section on Argon Between 95 and 720 MeV
S. Martynenko, B. Bhandari, J. Bian +72
We report an extended measurement of the neutron cross section on argon in the energy range of 95-720 MeV. The measurement was obtained with a 4.3-hour exposure of the Mini-CAPTAIN…
Topological quantum transition driven by charge-phonon coupling in higher-order topological insulators
Congwei Lu, Mei Zhang, Haibo Wang +2
We investigate a second-order topological quantum transition of a modified Kane-Mele model driven by electron-phonon interaction. The results show that the system parameters of the…
Feature-aware Diversified Re-ranking with Disentangled Representations for Relevant Recommendation
Zihan Lin, Hui Wang, Jingshu Mao +4
Relevant recommendation is a special recommendation scenario which provides relevant items when users express interests on one target item (e.g., click, like and purchase). Besides…
Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation
Shengming Li, Guangcong Zheng, Hui Wang +4
Denoising Diffusion Probabilistic Model (DDPM) is able to make flexible conditional image generation from prior noise to real data, by introducing an independent noise-aware classi…
Optimizing Shoulder to Shoulder: A Coordinated Sub-Band Fusion Model for Real-Time Full-Band Speech Enhancement
Guochen Yu, Andong Li, Wenzhe Liu +3
Due to the high computational complexity to model more frequency bands, it is still intractable to conduct real-time full-band speech enhancement based on deep neural networks. Rec…
DMF-Net: A decoupling-style multi-band fusion model for full-band speech enhancement
Guochen Yu, Yuansheng Guan, Weixin Meng +2
For the difficulty and large computational complexity of modeling more frequency bands, full-band speech enhancement based on deep neural networks is still challenging. Previous st…