EUROSPEECH 2003 - INTERSPEECH 2003 8th European Conference on Speech Communication and Technology Geneva, Switzerland September 1-4, 2003

Fitting Class-Based Language Models into Weighted Finite-State Transducer Framework

Pavel Ircing, Josef Psutka

University of West Bohemia in Pilsen, Czech Republic

In our paper we propose a general way of incorporating class-based language models with many-to-many word-to-class mapping into the finite-state transducer (FST) framework. Since class-based models alone usually do not improve the recognition accuracy, we also present a method for an efficient language model combination. An example of a word-to-class mapping based on morphological tags is also given. Several word-based and tag-based language models are tested in the task of transcribing Czech broadcast news. Results show that class-based models help to achieve a moderate improvement in recognition accuracy.

Full Paper

Bibliographic reference.  Ircing, Pavel / Psutka, Josef (2003): "Fitting class-based language models into weighted finite-state transducer framework", In EUROSPEECH-2003, 1873-1876.