Analysis of morph-based speech recognition and the modeling of out-of-vocabulary words across languages


Creutz M., Hirsimäki T., Kurimo M., Puurula A., Pylkkönen J., Siivola V., ...Daha Fazla

Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2007, Rochester, NY, Amerika Birleşik Devletleri, 22 - 27 Nisan 2007, ss.380-387, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: Rochester, NY
  • Basıldığı Ülke: Amerika Birleşik Devletleri
  • Sayfa Sayıları: ss.380-387
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

We analyze subword-based language models (LMs) in large-vocabulary continuous speech recognition across four "morphologically rich" languages: Finnish, Estonian, Turkish, and Egyptian Colloquial Arabic. By estimating n-gram LMs over sequences of morphs instead of words, better vocabulary coverage and reduced data sparsity is obtained. Standard word LMs suffer from high out-of-vocabulary (OOV) rates, whereas the morph LMs can recognize previously unseen word forms by concatenating morphs. We show that the morph LMs generally outperform the word LMs and that they perform fairly well on OOVs without compromising the accuracy obtained for in-vocabulary words. © 2007 Association for Computational Linguistics.