Automatic Transcription of Courtroom Recordings in the JUMAS project.
Daniele Falavigna, Diego Giuliani, Roberto Gretter, Jonas Lööf, Christian Gollan, Ralf Schlüter, Hermann Ney · 2009
Abstract. In this paper we present ongoing work on speech recognition for the judicial domain, performed in the European project JUMAS (Judicial management for digital library semantics.) The specific challenges for courtroom speech recognition are discussed, and the development of speech recognition systems for Italian and Polish are described. The results achieved on the target domain are presented and discussed. 1