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

 A GREAT MATHEMATICAL TRUTH : SQUARE ROOT TWO IS AN INVISIBLE PART & PACEL OF CIRCLE (118th Geometrical construction on Real Pi)

 Square root two was introduced by Pythagorean Hippasus of Metapontum representing the diagonal of the square. In March 1998, it was discovered that the same square root two, plays an important role in deciding the...

 Savitzky-Golay Filter Based Vertical Handoff between LTE and WIFI Network

 Heterogeneous network is a network connecting computers and other devices with different operating systems. Wireless networking is becoming an increasingly important and popular way of providing global informatio...

 Studies on Rhizosphere and Rhizoplane Microflora of Tomato (Lycopersicon esculentum Mill) Seedlings

 Investigations were carried out on the rhizosphere and rhizoplane microflora of tomato (Lycopersicon esculentum) seedlings planted in Amugwu village of Obige Obukpa in Nsukka Local Government Area of Enugu State,...

 An Efficient Instruction-Level Energy Estimation Model for Embedded Systems

 To optimize the energy consumption embedded systems, the estimation of energy consumption of the embedded applications are very important. This paper proposes a simple but effective instruction-level energy estim...

 SINGLE PHASE TO THREE PHASE POWER CONVERSION USING PWM TECHNIQUE

 The power electronics device which converts DC power to AC power at required output voltage and frequency level is known as inverter. Multilevel inverter is to synthesize a near sinusoidal voltage from several...

Download PDF file
  • EP ID EP100275
  • DOI -
  • Views 100
  • 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