Learn More
Recent progress in acoustic modeling with deep neural network has significantly improved the performance of automatic speech recognition systems. However, it remains as an open problem how to rapidly adapt these networks with limited, unsupervised, data. Most existing methods to adapt a neural network involve modifying a large number of parameters thus(More)
Social networks have become more and more popular in recent years. This popularity creates a need for personalization services to recommend tweets, posts (information) and celebrities organizations (information sources) to users according to their potential interest. Tencent Weibo (microblog) data in KDD Cup 2012 brings one such challenge to the researchers(More)
We in this paper present the model for our participation (BCMI) in the CoNLL-2012 Shared Task. Following the work of (Lee et al., 2011), we extend their English deterministic corefer-ence resolution model to Chinese. This paper describes a pure rule-based method, which assembles different filters in a proper order. Different filters handle different(More)
Deep neural networks (DNNs) and deep learning approaches yield state-of-the-art performance in a range of tasks, including speech recognition. However, the parameters of the network are hard to analyze, making network regularization and robust adaptation challenging. Stimulated training has recently been proposed to address this problem by encouraging the(More)
Rapid adaptation of deep neural networks (DNNs) with limited unsupervised data remains a significant challenge. This paper investigates the combination of two schemes that have been proposed to address this problem: i-vector representations and multi-basis adaptive neural networks (MBANNs). Two approaches for combining these schemes together are described.(More)
A lot of interest has been risen in the last years on the adaptation of deep neural network (DNN) acoustic models, as the latter become the state-of-art in automatic speech recognition. This work focuses on approaches that allow for rapid and robust adaptation of such models. First, i-vectors are added to the DNN input as speaker-informed features. An(More)
High energy density, low cost and environmental friendliness are the advantages of lithium-sulfur (Li-S) battery which is regarded as a promising device for electrochemical energy storage systems. As one of the important ingredients in Li-S battery, the binder greatly affects the battery performance. However, the conventional binder has some drawbacks such(More)
Given the size of modern cities in the urbanising age, it is beyond the perceptual capacity of most people to develop a good knowledge about the beauty and ugliness of the city at every street corner. Correspondingly, for planners, it is also difficult to accurately answer questions like 'where are the worst-looking places in the city that regeneration(More)
Organic-inorganic metal halide perovskites have recently demonstrated outstanding efficiencies in photovoltaics as well as highly promising performances for a wide range of optoelectronic applications such as lasing, light emission, optical detectors, and even for radiation detection. Key to the realization of functional perovskite micro/nanosystems on the(More)