In Computer Vision, two-dimensional shape classifcation is a complex and well studied topic, often basic for three-dimensional object recognition. Object contours are a widely cho...
Abstract. In this article, we propose the use of suffix arrays to efficiently implement n-gram language models with practically unlimited size n. This approach, which is used with ...
In the context of open environments like the Semantic Web, knowledge-based applications with autonomous knowledge sources have recently gained increased interest. For such sources...
Tina Froehner, Matthias Nickles, Gerhard Weiß...
Abstract. This paper describes research in understanding the requirements for complex information systems that are constructed from one or more generic COTS systems. We argue that,...
Ian Sommerville, Russell Lock, Tim Storer, John Do...
This paper focuses on confidence scores for use in acoustic model adaptation. Frame-based confidence estimates are used in linear transform (CMLLR and MLLR) and MAP adaptation. ...