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

ANALYSIS OF TRACE METAL CONTENT IN CHILLIE POWDER AVAILABLE IN THE SRI LANKAN MARKET

Chilie ( Capsicum annuum L.) powder is the dried, pulverized fruit of chilies and used as a spice to add pungency flavour to the dish. This study was conducted to investigate the trace metal content in c...

 A LOW-COST PMSG TOPOLOGY AND CONTROL STRATEGY FOR SMALLSCALE WIND POWER GENERATION SYSTEMS

 Developing a low-cost power converter for small-scale wind turbine systems using permanent magnet synchronous generators (PMSG) is one of the hot topics in the wind power generation research. Using minimum number o...

 COMPILATION OF ALTERNATIVE BUILDING COMPONENTS AND COMMON DISTRESSES FOUND THROUGH BUILDING CONDITION ASSESSMENT

 Buildings being constructed for residential or offices by government or commercial constructions are basically to fulfill demand of shelter due to high increase in the population, change in economic levels, obsole...

 Web Usage Mining and Internet User Behaviour in Web: A Survey

 In recent years the growth of the World Wide Web exceeded all expectations. Today, there are several billions of HTML documents, Pictures and other multimedia files available via Internet and the number is still r...

 Administration of Information in Higher Education-Role of ICT

 A good Higher Education System is required for overall prosperity of a nation. A tremendous growth in the higher education sector had made the administration of higher Education institutions complex. Many research...

Download PDF file
  • EP ID EP100275
  • DOI -
  • Views 83
  • 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