No abstract

Dialogue move recognition is taken as being representative of a class of spoken language applications where inference about high level semantic meaning is required from lower level acoustic, phonetic or word based features. Topic identication is another such application. In the particular case of inference from words, the multinomial distribution is shown to be inadequate for modelling word frequencies, and the multivariate Poisson is a more reasonable choice. Zipf's law is used to model a prior distribution. This more rigorous mathematical formulation is shown to improve dialogue move classication both subjectively and quantitatively.

No abstract

ROCKIT is a strategic roadmapping action in the area of multimodal conversational interaction technologies funded as a support action by the EU during 2014 and 2015. We envisage a future in which human-human, human-machine, and human-environment communication are not hampered by differences in language capability, accessibility, or knowledge of the technology, and where security and privacy are built in. These future conversational interaction technologies will enable interaction, collaboration, creativity, and information access within a vast, dynamic, heterogeneous, and partly ephemeral information space. ROCKIT is developing a roadmap to achieve this vision, linking research and innovation activities, and connecting a broad range of stakeholders. In this paper we present the ROCKIT roadmapping process, together with five target scenarios, which we believe can form a basis for discussion and engagement at the ICMI workshop which can further progress the community roadmap.

The need for a small bleed-off gas-turbine engine arose when the large turbojet and turboprop aircraft engines were introduced into military service. The problem of starting turbojet and turboprop aircraft engines became more acute as the starting power requirements began to exceed the practical weight and size limits of electric starters. As a result, development of a pneumatic starting system was undertaken. To make the low-pressure air starter practical, it was necessary to have a small, lightweight source of compressed air. The small gas-turbine bleed-off compressor unit was developed for this purpose. This paper describes the development procedure and details of this type engine as it now stands. So far only a few thousand units have been produced, but cost reductions are expected as use for these small gas-turbine engines increases.