13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Investigation of Maximum Entropy Hybrid Language Models for Open Vocabulary German and Polish LVCSR

M. Ali Basha Shaik, Amr El-Desoky Mousa, Ralf Schlüter, Hermann Ney

Human Language Technology and Pattern Recognition – Computer Science Department, RWTH Aachen University, Aachen, Germany

For languages like German and Polish, higher numbers of word inflections lead to high out-of-vocabulary (OOV) rates and high language model (LM) perplexities. Thus, one of the main challenges in large vocabulary continuous speech recognition (LVCSR) is recognizing an open vocabulary. In this paper, we investigate the use of mixed type of sub-word units in the same recognition lexicon. Namely, morphemic or syllabic units combined with pronunciations called graphones, normal graphemic morphemes or syllables, along with full-words. In addition, we investigate the suitability of hybrid mixed-unit N-grams as features for Maximum Entropy LM along with adaptation. We achieve significant improvements in recognizing OOVs and word error rate reductions for German and Polish LVCSR compared to the conventional full-word approach and state-of-the-art N-gram mixed type hybrid LM.

Index Terms: open vocabulary, maximum entropy

Full Paper

Bibliographic reference.  Basha Shaik, M. Ali / Mousa, Amr El-Desoky / Schlüter, Ralf / Ney, Hermann (2012): "Investigation of maximum entropy hybrid language models for open vocabulary German and Polish LVCSR", In INTERSPEECH-2012, 1071-1074.