I n this paper, we address the problem of isolated word recognition of speech under various stressed speaking conditions. The niain objective is to formulate an alternate training algorithm for hidden Markov model recognition, which better characterizes actual speech production under stressed speaking styles such as slow, loud and Lombard effect, without the need for collecting such stressed sp...

Department of Pure and Applied Mathematics, University of Padova, Italy In this report we present preliminary results of a study on the relationship between informal out-of-school and formal in-school mathematics and the ways each can inform the other in the development of new mathematical knowledge, in this case concerning computation in base 12, 24 or 60. This study is based on a teaching exp...

A novel two-channel algorithm is proposed in this paper for discriminative training of Hidden Markov Models (HMMs). It adjusts the symbol emission coefficients of an existing HMM to maximize the separable distance between a pair of confusable training samples. The method is applied to identify the visemes of visual speech. The results indicate that the two-channel training method provides bette...

We propose a method which can detect events in videos by modeling the change in appearance of the event participants over time. This method makes it possible to detect events which are characterized not by motion, but by the changing state of the people or objects involved. This is accomplished by using object detectors as output models for the states of a hidden Markov model (HMM). The method ...

K. Pawelzik MPI f. Stromungsforschung Bunsenstr. 10 37073 Gottingen, Germany We present a method for the analysis of nonstationary time series with multiple operating modes. In particular, it is possible to detect and to model both a switching of the dynamics and a less abrupt, time consuming drift from one mode to another. This is achieved in two steps. First, an unsupervised training method p...

There has been a great deal of recent interest in statistical models of 2D landmark data for generating compact deformable models of a given object. This paper extends this work to a class of parametrised shapes where there are no landmarks available. A rigorous statistical framework for the eigenshape model is introduced, which is an extension to the conventional Linear Point Distribution Mode...

This paper presents a way of possible implementation of teaching process based on interdisciplinary correlation. Interdisciplinary relationship between biology (bird migration) and geography (the basic features of countries through which white storks travel to their wintering grounds in Africa) is suggested in this paper. Such interdisciplinary approach should make the teaching process effectiv...