Using Part of Speech N-Grams for Improving Automatic Speech Recognition of Polish

  • Aleksander Pohl
  • Bartosz Ziółko
Conference paper

DOI: 10.1007/978-3-642-39712-7_38

Part of the Lecture Notes in Computer Science book series (LNCS, volume 7988)
Cite this paper as:
Pohl A., Ziółko B. (2013) Using Part of Speech N-Grams for Improving Automatic Speech Recognition of Polish. In: Perner P. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 2013. Lecture Notes in Computer Science, vol 7988. Springer, Berlin, Heidelberg

Abstract

This paper investigates the usefulness of a part of speech language model on the task of automatic speech recognition. The develped model uses part of speech tags as categories in a category-based language model. The constructed model is used to re-score the hypotheses generated by the HTK acoustic module. The probability of a given sequence of words is estimated using n-grams with Witten-Bell backoff.

The experiments presented in this paper were carried out for Polish. The best obtained results show that the part-of-speech-only language model trained on a 1-million manually tagged corpus reduces the word error rate by more than 10 percentage points.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Aleksander Pohl
    • 1
    • 2
  • Bartosz Ziółko
    • 1
  1. 1.Department of ElectronicsAGH University of Science and TechnologyKrakówPoland
  2. 2.Department of Computational LinguisticsJagiellonian UniversityKrakówPoland

Personalised recommendations