Zero crossing rate and short term energy as a cue for sex detection with reference to Assamese vowels

The aim of this paper is to find distinction between male and female by separating voiced, unvoiced and silenced parts of speech signal. The methods are based on calculation of zero crossing rate (ZCR) and short term energy (STE). In the present study we have considered 8 Assamese vowels to analyze and compare the ZCR and STE values for both male and female informants. Experimental results show that the female informant´s total and average values of energy and zero crossing rates of voice segments is far more than male informant´s.