Slovak Automatic Dictation System for Judicial Domain Milan Rusko 1(&) , Jozef Juhár 2 , Marián Trnka 1 , Ján Staš 2 , Sakhia Darjaa 1 , Daniel Hládek 2 , Róbert Sabo 1 , Matúš Pleva 2 , Marián Ritomsky ´ 1 , and Martin Lojka 2 1 Institute of Informatics, Slovak Academy of Sciences, Dúbravská cesta 9, 845 07 Bratislava, Slovakia {milan.rusko,marian.trnka,utrrsach,robert.sabo, marian.ritomsky}@savba.sk 2 Department of Electronics and Multimedia Communications, Faculty of Electrical Engineering and Informatics, Technical University of Košice, Park Komenského 13, 042 00 Košice, Slovakia {jozef.juhar,jan.stas,daniel.hladek,matus.pleva, martin.lojka}@tuke.sk Abstract. This paper describes the design, development and evaluation of the Slovak dictation system for the judicial domain. The speech is recorded using a close-talk microphone and the dictation system is used for on-line or off-line automatic transcription. The system provides an automatic dictation tool in Slovak for the employees of the Ministry of Justice of the Slovak Republic and all the courts in Slovakia. The system is designed for on-line dictation and off- line transcription of legal texts recorded in acoustical conditions of typical office. Details of the technical solution are given and the evaluation of different versions of the system is presented. Keywords: Automatic speech recognition  Slovak language  Judicial domain 1 Introduction Dictation systems for major world languages have been available for years. The Slovak language, a Central European language spoken by a relatively small population (around 5 million), suffers from the lack of speech databases and linguistic resources, and these are the primary reasons for the absence of a dictation system until recently. We describe the design, development and evaluation of a Slovak dictation system named APD (Automaticky ´ Prepis Diktátu – Automatic Transcription of Dictation) for the judicial domain. The development of the automatic transcription systems for the judicial domain is a very challenging task from the research and development point of view. (see e.g. [1]). On the other hand there is a market demand for such technologies. Court room speech transcription is considered as one of the greatest challenges for the front-end of speech recognition and the authors with the cooperation with the Ministry of Justice of the Slovak Republic decided to divide the task into three stages. Ó Springer International Publishing Switzerland 2014 Z. Vetulani and J. Mariani (Eds.): LTC 2011, LNAI 8387, pp. 16–27, 2014. DOI: 10.1007/978-3-319-08958-4_2