Corrective models for speech recognition of inflected languages

Izhak Shafran, Keith Hall
2006 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing - EMNLP '06   unpublished
This paper presents a corrective model for speech recognition of inflected languages. The model, based on a discriminative framework, incorporates word ngrams features as well as factored morphological features, providing error reduction over the model based solely on word n-gram features. Experiments on a large vocabulary task, namely the Czech portion of the MALACH corpus, demonstrate performance gain of about 1.1-1.5% absolute in word error rate, wherein morphological features contribute
more » ... ures contribute about a third of the improvement. A simple feature selection mechanism based on χ 2 statistics is shown to be effective in reducing the number of features by about 70% without any loss in performance, making it feasible to explore yet larger feature spaces.
doi:10.3115/1610075.1610130 fatcat:lhgnadho3bbfznfcvtcbepepb4