PERFORMANCE EVALUATION OF STATISTICAL APPROACHES FOR AUTOMATIC TEXT-INDEPENDENT GENDER IDENTIFICATION SYSTEM

Abstract

 In this paper, robust feature for Automatic text-independent Gender Identification System has been explored. Through different experimental studies, it is demonstrated that the timing varying speech related information can be effectively captured using Hidden Markov Models (HMMs) than Gaussian Mixture Models (GMMs) . The study on the effect of feature vector size for good Gender Identification demonstrates that, feature vector size in the range of 18-22 can capture Gender related information effectively for a speech signal sampled at 16 kHz, it is established that the proposed Gender Identification system requires significantly less amount of data during both during training as well as in testing. The Gender Identification study using robust features for different states and different mixtures components, training and test duration has been exploited on TIMIT database.

Authors and Affiliations

R. Rajeswara Rao

Keywords

Related Articles

 Survey of Smart Irrigation System

 Today we are living in 21st century where automation is playing important role in human life. Automation allows us to control appliances automation not only provides comfort but also reduces energy, efficiency and...

 MODELLING AND CONTROL FOR COMPOSITION OF NON-ISOTHERMAL CSTR BY USING FUZZY

 As a matter of fact, several chemical or petrochemical industries are still using the old technology which are conventional control; one of it is PID controller. PID controller stills had a lot of weaknesses t...

 UI AUTOMATION FOR IVR SYSTEM

 As we know Software testing is quite a tedious and extravagant work ,so there is a need of overcoming this problem by my making some tool to reduce human involvement and reduce time to perform nearly similar tasks...

 Comparison of Different Natural Fiber Reinforced Concrete: Review

 In recent years, a great deal of interest in concrete leads to the most frequently used construction material in the world. The fiber reinforcement can effectively improve the toughness, shrinkage and durability c...

 Wide-Band Current Starved Ring CMOS Voltage Controlled Oscillator (VCO) using 0.18 μm CMOS Technology

 This paper describes a design and implementation of Current Starved CMOS Voltage Controlled Oscillator based on Ring Oscillator. Efforts are made to design a CMOS Voltage controlled oscillator having wide frequenc...

Download PDF file
  • EP ID EP100275
  • DOI -
  • Views 104
  • Downloads 0

How To Cite

R. Rajeswara Rao (2015).  PERFORMANCE EVALUATION OF STATISTICAL APPROACHES FOR AUTOMATIC TEXT-INDEPENDENT GENDER IDENTIFICATION SYSTEM. International Journal of Engineering Sciences & Research Technology, 4(1), 535-541. https://europub.co.uk/articles/-A-100275