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

 REAL TIME PILGRIMS TRACKING WITH FEEDBACK

 Now a days due to the increasing crude of pilgrims at the holy areas, during pilgrimage the management authorities faces so many problems regarding the crowd control, pilgrim identification and tracking and provid...

 REVIEW ON GRID INTERFACING OF MULTIMEGAWATT PHOTOVOLTAIC INVERTERS

 This paper presents review on the latest development of control of grid connected photovoltaic energy conversion system. Also this paper present existing systems control algorithm for three-phase and single phase...

Vehicular Trip Generation Modelling in Maiduguri Metropolis

The purpose of the trip and modeling process is to identify those meaningful determinants of trip making behavior, and express their effect in mathematical way so that they can be used with confidence as a predictive to...

 [b]Secure Symmetric Key Algorithm [SSKA] For Information Exchange Using Modulo 67 [/b]

 The e-data usage is increasing day by day. Nowadays exchange of data over the internet is increased higher than before. Security is the main issue in communication over a network. Protection must be given against...

 Graph Tracer – Simultaneous Vessel Identification to Detect the Retinal Crossover Points

 Retinal vessel morphology is highly related with hypertension, coronary heart disease, and stroke and the changes in retinal vessel identification are considered as earlier diagnosis of the cardiovascular disease....

Download PDF file
  • EP ID EP100275
  • DOI -
  • Views 93
  • 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