iscuss their usability and performance. 1.0 Introduction Multilinguality will take on spoken form when information services are to extend beyond national boundaries or across language groups. Database access by speech will need to handle multiple languages to service customers from different language groups. Public service operators (emergency, police, telephone operators and others) frequently receive requests from foreigners unable to speak the national language. Already multilingual spoken language services are growing. Telephone companies in the US (AT&T Language Line), Europe and Japan now offer language translation services over the telephone, provided by human operators. Movies and television broadcasts are routinely translated and Interactive Translation of Conversational Speech 2 delivered either by dubbing, subtitles or multilingual transcripts. With the drive of automating information services, therefore, comes a growing need for automate

A scalable supervised algorithm

Spelled letter recognition over the telephone line is essential for applications that involve names or addresses. In this paper we discuss the implementation and present results of a speaker independent spelled letter recognizer, trained and tested on the European project SPEECHDAT corpus. The system was implemented using HTK V2.0 (Hidden Markov Model Toolkit) software development tool and the speech signal was modelled using Hidden Markov Models (HMM).