This paper describes a simple method for significantly improving Tandem features used to train acoustic models for large-vocabulary speech recognition. The linear activations at ...
In this paper, a generalized multimedia database data model based on MPEG-7 named G3M is proposed and formally defined. Different from those XML Database Management System (DBMS) ...
This paper explores ways by which multiple authors can annotate 3D models from multiple viewpoints in a 3D collaborative environment, with particular reference to the environment ...
Rieko Kadobayashi, Julian Lombardi, Mark P. McCahi...
Development of sound approaches and software tools for specification, assembly, and deployment of composite Web services from independently developed components promises to enhan...
Jyotishman Pathak, Samik Basu, Robyn R. Lutz, Vasa...
This paper develops a mathematical characterisation of object-oriented concepts by defining an observation-oriented semantics for an object-oriented language (OOL) with a rich var...