Open Domain Speech Translation: From Seminars and Speeches to Lectures

Christian Fügen, Muntsin Kolss, Matthias Paulik, Sebastian Stüker, Tanja Schultz, Alex Waibel
This paper describes our ongoing work in domain unlimited speech translation. We describe how we developed a lecture translation system by moving from speech translation of European Parliament Plenary Sessions and seminar talks to the open domain of lectures. We started with our speech recognition (ASR) and statistical machine translation (SMT) 2006 evaluation systems developed within the framework of TC-Star (Technology and Corpora for Speech to Speech Translation) and CHIL (Computers in the
more » ... (Computers in the Human Interaction Loop). The paper presents the speech translation performance of these systems on lectures and gives an overview of our final real-time lecture translation system.
doi:10.5445/ir/1000008629 fatcat:4c6l4y7m3reibi22tgdic4xd7y