Binary classification performances of emotion classes for Turkish Emotional Speech Türkçe Duygusal Konuşma Için Duygu Siniflarinin Ikili Siniflandirma Performanslari

Oflazoglu Ç., Yildirim S.

2015 23rd Signal Processing and Communications Applications Conference, SIU 2015, Malatya, Türkiye, 16 - 19 Mayıs 2015, ss.2353-2356, (Tam Metin Bildiri) identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/siu.2015.7130352
  • Basıldığı Şehir: Malatya
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.2353-2356
  • Anahtar Kelimeler: binary classification, categorical classification, emotional speech, pattern recognition, TurES database
  • Hatay Mustafa Kemal Üniversitesi Adresli: Evet

Özet

Emotion recognition from speech plays important role for natural human-computer interaction. This study investigates binary classification performances of 4 fundamental emotion classes in Turkish Emotional Speech (TurES) Database using acoustic features for various classifiers. Results shows that Angry emotion class has higher classification rate (70%-80%) than others; lowest classification rate is obtained as 64% for Happy-Neutral emotion pair. Best classification results are obtained with J48 (C4.5) classifier for all emotion pairs.