Comparison of Different Normalization Techniques on Speakers’ Gender Detection

Journal Title: Mehmet Akif Ersoy Üniversitesi Uygulamalı Bilimler Dergisi - Year 2018, Vol 2, Issue 2

Abstract

In this study, the effect of Short-time Mean and Variance Normalization (STMVN), Shorttime Cepstral Mean and Scale Normalization (STMSN), Min-Max Normalization, Z-Score Normalization and Standard Deviation Normalization techniques on the classification performance was investigated in determining speakers’ gender. In the study, voice records which belongs to 192 male and 192 female speakers from TIMIT data set were used as data set. Features were extracted from Mel Frequency Cepstral Coefficients (MFCC) technique by using voice records and extracted features’ dimension was reduced to Principal Component Analysis (PCA), then normalized with different techniques. Support Vector Machine (SVM) was used as classifier. As a result of study, it was observed that, the highest accuracy in speakers’ gender estimation is obtained as 98.18% from features which were normalized with Standard Deviation Normalization technique and other normalization techniques were reduced accuracy.

Authors and Affiliations

Serhat Celil İleri, Armağan Karabina, Erdal Kılıç

Keywords

Related Articles

Kuantum Teorisinin Yorumu ve Doğanın Rolü

The connection involving classical and quantum theory is of main value to the philosophy of physics, and any kind of decryption of quantum mechanics needs to explain it. Aside from gravity, quantum mechanics clarifies pr...

A New Sofa Bed Mechanism System For Furniture Industry

Today, the works that improve ergonomics and human comfort in the furniture sector are consistently increasing. In addition to this, improving the current situation of the mechanism systems, which are used in the widely...

AISI D2 Soğuk İş Takım Çeliğinin Elektro Erozyon Tekniği İle İşlenebilirliğinin Deneysel Olarak İncelenmesi

Bu çalışmada elektro erozyon ile işlemede (EEİ) iş parçası ve elektrot çifti için işleme parametrelerinin etkileri deneysel olarak incelenmiştir. Deneysel çalışmada elektrot olarak bakır, iş parçası malzemesi olarak AISI...

Restructuring The Welfare State Model in Turkey and Its Affect on Female Employment Issues

In this study, female employment in Turkey is examined in the Welfare State Model axis. Within the scope of the study, the contribution of women's labor to the economy of the country was evaluated in the light of socioec...

Uluslararası Kredi Derecelendirme Kuruluşlarının Türkiye İçin Yapmış Oldukları Not Açıklamalarının Hisse Senedi Piyasaları Üzerine Etkisi: BIST 100’de Seçili Sektör Endeksleri Üzerine Uygulama

Son dönemlerde bilgi ve iletişim teknolojilerinde yaşanan gelişmeler ve sermayenin hareketini sınırlayan engellerin ortadan kalkması sonucunda finansal piyasalar arasında ki entegrasyon giderek artmıştır. Yaşanan gelişme...

Download PDF file
  • EP ID EP418309
  • DOI 10.31200/makuubd.410625
  • Views 185
  • Downloads 0

How To Cite

Serhat Celil İleri, Armağan Karabina, Erdal Kılıç (2018). Comparison of Different Normalization Techniques on Speakers’ Gender Detection. Mehmet Akif Ersoy Üniversitesi Uygulamalı Bilimler Dergisi, 2(2), 1-12. https://europub.co.uk/articles/-A-418309