Development of the 2003 CU-HTK conversational telephone speech transcription system

This paper describes the development of the 2003 CU-HTK large vocabulary speech recognition system for Conversational Telephone Speech (CTS). The system was designed based on a multi-pass, multi-branch structure where the output of all branches is combined using system combination. A number of advanced modelling techniques such as Speaker Adaptive Training, Heteroscedastic Linear Discriminant Analysis, Minimum Phone Error estimation and specially constructed Single Pronunciation dictionaries were employed. The effectiveness of each of these techniques and their potential contribution to the result of system combination was evaluated in the framework of a state-of-the-art LVCSR system with sophisticated adaptation. The final 2003 CU-HTK CTS system constructed from some of these models is described and its performance on the DARPA/NIST 2003 Rich Transcription (RT-03) evaluation test set is discussed.

PASREG 2003: International workshop on processing and applications of superconducting (RE)BCO large grain materials

This issue of Superconductor Science and Technology is edited by Murakami, M., Cardwell, D.A., Salama, K., Krabbes, G., Habisreuther, T. and Gawalek, W. It contains 42 selected papers from the PASREG 2003 international workshop, held in Jena, Germany, 30 June - 2 July 2003. The workshop was organised by the Institut fur Physikalische Hochtechnologie, Jena, Germany and was the fourth in the series of workshops first held in Cambridge, UK, in 1997.