Hybrid registration schemes are a powerful alternative to fully automatic registration algorithms. Current methods for hybrid registration either include the landmark information a...
Many sequence labeling tasks in NLP require solving a cascade of segmentation and tagging subtasks, such as Chinese POS tagging, named entity recognition, and so on. Traditional p...
In this paper, we propose a novel feature space adaptation technique to improve the robustness of speech recognition in noisy environments. Histogram equalization (HEQ) is an effe...
Datapath width optimization is very effective for reducing the area of a custom-made embedded system. The trivial way of optimization is to iteratively customize, evaluate, and r...
Today‘s use of mobile phones is mostly for coordination purposes. It seems reasonable to assume that 3G and 4G high bandwidth systems will be used in a similar way. This paper th...