In this paper we report on automatic recognition of Japanese broadcast-news speech. We have been working on largevocabulary continuous speech recognition (LVCSR) for Japanese newspaper speech transcription and achieved reasonably good performance. We have recently applied our LVCSR system to transcribing Japanese broadcast-news speech. We extended the vocabulary to 20k words and trained the lan...

A newspaper content management system has to deal with a very heterogeneous information space as the experience in the Diari Segre newspaper has shown us. The greatest problem is to harmonise the different ways the involved users (journalist, archivists...) structure the newspaper information space, i.e. news, topics, headlines, etc. Our approach is based on ontology and differentiated universe...

Motion capture cannot generate cartoon-style animation directly. We emulate the rubber-like exaggerations common in traditional character animation as a means of converting motion capture data into cartoon-like movement. We achieve this using trajectory-based motion exaggeration while allowing the violation of link-length constraints. We extend this technique to obtain smooth, rubber-like motio...

In this paper, we introduce pyramid-adapted shearlet systems for the three-dimensional setting, and show how one can construct frames for L(R) with this particular shearlet structure. We then introduce a generalized three-dimensional cartoon-like image model class of piecewise C smooth functions with discontinuities on a C smooth surface with 1 < α ≤ 2 and show that pyramid-adapted shearlet sys...