The RWTH Aachen German and English LVCSR systems for IWSLT-2013
Mohamed Mahmoud Ali, Basha Shaik, Zoltan T ̈ uske, Simon Wiesler, Markus Nußbaum-Thom, Stephan Peitz, Ralf Schl ̈ uter, Hermann Ney, Limsi Cnrs · 2013
In this paper, German and English large vocabulary contin-uous speech recognition (LVCSR) systems developed by the RWTH Aachen University for the IWSLT-2013 evaluation campaign are presented. Good improvements are obtained with state-of-the-art monolingual and multilingual bottle-neck features. In addition, an open vocabulary approach us-ing morphemic sub-lexical units is investigated along with the language model adaptation for the German LVCSR. For both the languages, competitive WERs are achieved using system combination. 1.