期刊名称：International Journal of Electronics and Computer Science Engineering
电子版ISSN：2277-1956
出版年度：2012
卷号：1
期号：4
页码：2008-2014
出版社：Buldanshahr : IJECSE
摘要：language is man’s most important means of communication and speech its primary medium. Speech recognition is the ability of a computer to recognize general, naturally flowing utterances from a wide variety of users. 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 5 utterances spoken by10 peoples including 5 male and 5 female talkers (aged 19 to 25 years old). The differences of speech long term features including zero crossing rate and short term energy for different person is studied.
