Qingfeng Liu

Learn More
Fast adaptation of deep neural networks (DNN) is an important research topic in deep learning. In this paper, we have proposed a general adaptation scheme for DNN based on discriminant condition codes, which are directly fed to various layers of a pre-trained DNN through a new set of connection weights. Moreover, we present several training methods to learn(More)
We report applications of language technologies to analyzing historical documents in the Database for the Study of Modern Chinese Thoughts and Literature (DSMCTL). We studied two historical issues with the reported techniques: the conceptu-alization of " 華人 " and the attempt to institute constitutional monarchy in the late Qing dynasty. We also discuss(More)
Vascular endothelial growth factor (VEGF) is one of the major cytokines secreted by activated hepatic stellate cells (HSCs). VEGF is involved in hepatic angiogenesis and plays an important role in the development of liver fibrosis. TNP-470, an angiogenic inhibitor, attenuates the development of rat liver fibrosis with reduced angiogenesis, as demonstrated(More)
To investigate the possible pathways for transport of wheat germ agglutinin conjugated PEG-PLA nanoparticles (WGA-NP) into the brain after nasal administration. The nose-to-brain pathways were investigated using WGA-NP containing 6-coumarin (as a fluorescent marker) and 125I-labeled WGA-NP. Ex vivo imaging analysis was also employed to visualize the(More)
The hybrid deep neural network (DNN) and hidden Markov model (HMM) has recently achieved dramatic performance gains in automatic speech recognition (ASR). The DNN-based acoustic model is very powerful but its learning process is extremely time-consuming. In this paper, we propose a novel DNN-based acoustic modeling framework for speech recognition, where(More)