Voice and Unvoiced Classification Using Fuzzy Logic

Conference Paper

Ali, Mohammed Algabri, Mansour Alsulaiman, Ghulam Muhammad, Mohammed Zakariah, Mohamed Bencherif, Zulfiqar . 2015

• Conference Name: The 19th International Conference on Image Processing, Computer Vision, & Pattern Recognition
• Conference Location: Las Vegas, Nevada, USA
• Conference Date: Monday, July 27, 2015

Publication Abstract

In this paper, we proposed a system for automatic classification of speech. A speech signal contains three different regions voiced, unvoiced and silence. In the proposed system, Zero-Crossing rate and short term energy are used in a fuzzy logic control this classification. Arabic digits of the KSU database is used to test our proposed method. The proposed method achieves 2.5 % error between human classification and automatic classification using this method.