15th Annual Conference of the International Speech Communication Association

September 14-18, 2014

RWTH LVCSR Systems for Quaero and EU-Bridge: German, Polish, Spanish and Portuguese

M. Ali Basha Shaik, Zoltán Tüske, M. Ali Tahir, Markus Nußbaum-Thom, Ralf Schlüter, Hermann Ney

RWTH Aachen University, Germany

In this paper, German, Polish, Spanish, and Portuguese large vocabulary continuous speech recognition (LVCSR) systems developed by the RWTH Aachen University are presented. All the above mentioned systems for the aforementioned languages are used for the Quaero and EU-Bridge project evaluations. The LVCSR systems developed for these competitive evaluations focus on various domains like broadcast news, podcasts and lecture domain. Transcription of the speech for these tasks is challenging due to huge variability in the acoustic conditions and a significant portion of audio data includes spontaneous speech. Good improvements are obtained using state-of-the-art multilingual bottleneck features, minimum phone error trained acoustic models, language model (LM) adaptation and confusion-network based system combination. In addition, an open vocabulary approach using morphemic units is investigated along with the LM adaptation for the German LVCSR.

Full Paper

Bibliographic reference.  Shaik, M. Ali Basha / Tüske, Zoltán / Tahir, M. Ali / Nußbaum-Thom, Markus / Schlüter, Ralf / Ney, Hermann (2014): "RWTH LVCSR systems for quaero and EU-bridge: German, Polish, Spanish and Portuguese", In INTERSPEECH-2014, 973-977.