Hindi Speaking Person Identification using Zero Crossing Rate
Arif Ullah Khan1, L.P.Bhaiya2, Sumit Kumar Banchhorr3
1Arif Ullah Khan ,Electronics& telecomm,CSVTU/RSR-RCET, Bhilai, India.
2Lalit P Bhaiya, Electronics& telecomm, CSVTU / RCET, Bhilai, India.
3Sumit Banchhor, Electronics & Telecomm, CSVTU/ GDR RCET, Bhilai, India.
Manuscript received on July 01, 2012. | Revised Manuscript received on July 04, 2012. | Manuscript published on July 05, 2012. | PP: 1-4 | Volume-2, Issue-3, July 2012. | Retrieval Number: B0558042212/2012©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: Information from speech recognition can be used in various ways in state of the art speaker recognition systems. This includes the obvious use of recognized words to enable the use of text dependent speaker modeling techniques. In this paper text dependent speaker identification method is used. This system contains training phase, the testing phase and recognition phase. In the training phase, the feature word is extracted. During the testing phase, feature matching takes place. The feature that extracted is stored in the data base. During the recognition phase, the features are extracted by same techniques and are compared with the template in the database. Differences of physiological properties of the glottis and vocal tracts are partly due to age, gender and/or person differences. Since these differences are related in the speech signal, acoustic measures related to those properties can be helpful for speaker identification. Acoustic measure of voice sources were extracted from 3 utterances spoken by 10 peoples including 5 male and 5 female talkers (aged 19 to 25 years old). In this paper, the eature of the extraction takes place by Zero Crossing Rate (ZCR).
Keywords: Speech recognition, feature extraction, zero-crossing rate.