Selection of optimal feature set in phoneme duration modeling

ÖZTÜRK Ö., Ciloglu T.

IEEE 14th Signal Processing and Communications Applications, Antalya, Türkiye, 16 - 19 Nisan 2006, ss.686-688 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Doi Numarası: 10.1109/siu.2006.1659801
  • Basıldığı Şehir: Antalya
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.686-688
  • Dokuz Eylül Üniversitesi Adresli: Evet

Özet

In order to increase the intelligibility and naturalness of synthetic speech, the prosodic entities such as segmental duration, pitch, and energy should be modelled appropriately. This study presents determination of the optimal feature subset for modeling segmental duration in Turkish using Classification and Regression Trees (CART) based on feature selection methods.