Classification problems with a very large or unbounded set of output categories are common in many areas such as natural language and image processing. In order to improve accuracy on these tasks, it is natural for a decision-maker to combine predictions from various sources. However, supervised data needed to fit an aggregation model is often difficult to obtain, especially if needed for multi...

The development of a multimodal Human-Robot Interface (HRI) involving mixed-initiative and context-awareness is complex and laborious. The integration of individual modalities (e.g., gesture recognition or speech output) and the design of natural human-robot interaction are two different tasks that both require their own expertise. In this paper, we consider three different roles that participa...

This paper describes the JHU system combination scheme used in WMT-11. The JHU system combination is based on confusion network alignment, and inherited the framework developed by (Karakos et al., 2008). We improved our core system combination algorithm by making use of TER-plus, which was originally designed for string alignment, for alignment of confusion networks. Experimental results on Fre...

A system to analyze live audio feeds using speech and speaker recognition is described. Multi-modal analysis of this nature calls for concurrent operations to transcribe speech, to partition it into acoustically homogeneous, single-speaker segments, and to identify the speaker in these segments. The architecture of such a system built at IBM is described along with the techniques used in the in...

We show how event extraction can be used for handling delayed response tasks with arbitrary delay periods between the stimulus and the cue for response. Our approach is based on a number of information processing levels, where the lowest level works on raw time-stepped based sensory data. This data is classified using an unsupervised clustering mechanism. The second level works on this classifi...