Comparison of language modeling approaches for Turkish broadcast news Türkçe haber bültenleri için dil modelleme yaklaşimlarinin karşilaştrmasi


Aksungurlu T., Parlak S., Sak H., SARAÇLAR M.

2008 IEEE 16th Signal Processing, Communication and Applications Conference, SIU, Aydın, Türkiye, 20 - 22 Nisan 2008, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/siu.2008.4632705
  • Basıldığı Şehir: Aydın
  • Basıldığı Ülke: Türkiye
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

In this paper, we investigate the performance of several language modeling approaches on a speech recognition system for Turkish Broadcast News. The agglutinative structure of Turkish introduces a high out-of-vocabulary rate and hence increases word error rate. To eliminate out-of-vocabulary problem, we utilize various sub-word models. In addition, we experiment with high vocabulary sizes. Since the models are statistical, we expect an improvement in performance as the amount of training data increases. We build word and sub-word language models using various amounts of corpora and compare their recognition performance. ©2008 IEEE.