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)
Language model is a vital part in modern state-of-art ASR systems. N-Gram LMs have been dominating the area of language modelling during last several decades. Recently, recurrent neural network language models (RNNLMs) present promising performance in many areas and various tasks [1, 2, 3, 4, 5, 6, 7, 8]. In this thesis, we aim to further explore recurrent(More)
Due to the limitation of radio spectrum resource and fast deployment of wireless devices, careful channel allocation is of great importance for mitigating the performance degradation caused by interference among different users in wireless networks. Most of existing work focused on fixed-width channel allocation. However, latest researches have demonstrated(More)