Speaker diarization is the task of partitioning an input stream into speaker homogeneous regions, or in other words, to determine "who spoke when." While approaches to t...
This paper describes a pilot study of a computer simulation called WIIS, which is designed to extend students' learning experience of the sizes of the objects beyond human vi...
This paper describes an extension to a multimodal system designed to improve Internet accessibility for the visually impaired. Here we discuss the novel application of a grid (pat...
Philip Strain, Graham McAllister, Emma Murphy, Rav...
Speaker diarization is originally defined as the task of determining “who spoke when” given an audio track and no other prior knowledge of any kind. The following article sho...
Many information sources use multiple modalities, such as textbooks, which contain both text and diagrams. Each captures information that is hard to express in the other, and evid...