Discriminative N-gram language modeling for Turkish


Arisoy E., Roark B., Shafran I., SARAÇLAR M.

INTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association, Brisbane, Avustralya, 22 - 26 Eylül 2008, ss.825-828, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: Brisbane
  • Basıldığı Ülke: Avustralya
  • Sayfa Sayıları: ss.825-828
  • Anahtar Kelimeler: Agglutinative languages, Discriminative language modeling, Speech recognition
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

In this paper Discriminative Language Models (DLMs) are applied to the Turkish Broadcast News transcription task. Turkish presents a challenge to Automatic Speech Recognition (ASR) systems due to its rich morphology. Therefore, in addition to word n-gram features, morphology based features like root n-grams and inflectional group n-grams are incorporated into DLMs in order to improve the language models. Various feature sets provide reductions in the word error rate (WER). Our best result is obtained with the inflectional group n-gram features. 1.0% absolute improvement is achieved over the baseline model and this improvement is statistically significant at p<0.001 as measured by the NIST MAPSSWE significance test. Copyright © 2008 ISCA.