In this paper we summarise the state-of-the-art for automatic speech recognition in automated Directory Assistance at the start of the 5th Framework project SMADA. Details are given about robust acoustic features for use in Distributed Speech Recognition, especially with respect to noise suppression. Then an overview is given of the confidence measures which are in use today, and their similari...

Analysis of the Implementation Calculation and Distribution SHU at KPRI SMADA SMA Negeri 2 Palangka Raya. The location this research is Raya which located Jalan K.S. Tubun No.02 Pahandut, City. This cooperative was formed on January 25, 1988 with a legal entity No: 1057/BH/XIX/1989. thesis written aim knowing implementation calculation distribution in Cooperative 2021; to find out 2021 accordan...

This paper introduces the IST-HLT project SMADA. This project started in January 2000 and it will run for three years. We present information on the topics to be addressed in the project; in addition some preliminary results are given. Information is given on functional specifications and technical and Human Factors evaluations of Automatic Directory Assistance systems in four European countrie...

This paper deals with the difficult task of recognition of a large vocabulary of proper names in a directory assistance application. Research on the European project SMADA has shown that there is a need of an elaborate and effective decision strategy that limits the risk of false automation. This paper proposes a new strategy which integrates, as well as a general decoder, a set of decoders spe...

So far most attempts to automate Directory Assistance services focused on private listings, because it is not known precisely how callers will refer to a business listings. The research de­ scribed in this paper, carried out in the SMADA project, tries to fill this gap. The aim of the research is to model the expres­ sions people use when referring to a business listing by means of rules, in or...

This paper presents the use of corpus linguistics techniques on supposedly “clean” corpora and identifies potential pitfalls. Our work relates to the task of filtering sensitive content, in which data security is strategically important for the protection of government and military information, and of growing importance in combating identity fraud. A naïve keyword filtering approach produces a ...