Comparison of Text-Dependent Method for Gender Identification
Sumit Kumar Banchhor1, S. K. Dekate2
1Sumit Kumar Banchhor, Department of Electronics and Telecommunication, Chhattisgarh Swami Vivekananda Technical University, Rungta College of Engineering and Technology, Bhilai, India.
2S. K. Dekate, Department of Electronics and Telecommunication, Chhattisgarh Swami Vivekananda Technical University, Rungta College of Engineering and Technology, Bhilai, India.
Manuscript received on August 19, 2011. | Revised Manuscript received on August 29, 2011. | Manuscript published on September 05, 2011. | PP: 164-167 | Volume-1 Issue-4, September 2011. | Retrieval Number: D0117081411/2011©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Differences of physiological properties of the glottis and the vocal track are partly due to age and/or gender differences. Since these differences are reflected in the speech signal, acoustic measures related to those properties can be helpful for automatic gender classification. Acoustics measures of voice sources were extracted from 10 utterances spoken by 20 male and 20 female talkers (aged 19 to 25 year old). The difference of speech long term features, including zero crossing rate, short time energy, and spectrum flux between male and female is studied. The result shows that the estimation of short time energy reflects more effectively, the difference in male and female voice than zero crossing rate and spectrum flux.
Keywords: Gender classification gender identification, voice source.