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

Environmental Accounting Approach to Emissions Cost Evaluation of A Cargo Aircraft During A Domestic Flight

Nowadays regarding the impact of environmental issues on the daily life applications and measures to prevent environmental pollution are dealt. Particularly after signing Kyoto Protocol and Paris Agreement these measures...

Estimation of Turkey Industrial Electricity Consumption with Artificial Neural Networks for the 2017-2023 Period

In the development of the countries, the industry played a big role and the industrial activities from the past to the present day progressed without slowing down. These developments have expanded their treasury by selli...

Lojistikte Taşıma Şekillerinin Belirlenmesi: Bir Kombine Taşımacılık Örneği

In this study, one of the major problems of Turkey; “transportation” is examined in logistics. The importance, applicability, advantages-disadvantages and the future of Combined Transport is discussed. The solution which...

İşgörenlerin Öznel İyi Olma Düzeylerinin Farklı Sosyo-Demografik Değişkenler Açısından İncelenmesi: Banka Çalışanları Üzerinde Bir Araştırma

The aim of the research is to determine whether the subjective well-being of individuals who are working in the banking sector differ according to some demographic variables (working bank type, sex, age, marital status,...

International Capital Controls, A Literature Investigation on Capital Control Applications of European and Asian Countries

The protectionist and intrusive approach, which is a result of the Keynesian thinking that has influenced international markets from 1929 to 1970, has now been replaced by more liberal and openly functioning markets. Whi...

Download PDF file
  • EP ID EP418309
  • DOI 10.31200/makuubd.410625
  • Views 177
  • 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