Classification of stress in speech using linear and nonlinear features

Classification of stress in speech using linear and nonlinear features

In this paper, three systems for classification of stress in speech are proposed. The first system makes use of linear short time Log Frequency Power Coefficients (LFPC), the second employs Teager Energy Operator (TEO) based Nonlinear Frequency Domain LFPC features (NF...

Ful tanımlama

Detaylı Bibliyografya
Asıl Yazarlar: Nwe, Tin Lay, Foo, Say Wei, De Silva, Liyanage C.
Diğer Yazarlar: School of Electrical and Electronic Engineering
Materyal Türü: Conference Paper
Dil:English
Baskı/Yayın Bilgisi: 2009
Konular:
DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
Online Erişim:https://hdl.handle.net/10356/90922
http://hdl.handle.net/10220/5964
Diğer Bilgiler
Özet:In this paper, three systems for classification of stress in speech are proposed. The first system makes use of linear short time Log Frequency Power Coefficients (LFPC), the second employs Teager Energy Operator (TEO) based Nonlinear Frequency Domain LFPC features (NFD-LFPC) and the third uses TEO based Nonlinear Time Domain LFPC features (NTD-LFPC).The systems were tested using SUSAS (Speech Under Simulated and Actual Stress) database to categorize five stress conditions individually. Results show that, the system using LFPC gives the highest accuracy, followed by the system using NFD-LFPC features. While the system using NTD-LFPC features gives the worst performance. For the system using linear LFPC features, the average accuracy of 84% and the best accuracy.

Benzer Materyaller