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：3
页码：1623-1628
出版社：Buldanshahr : IJECSE
摘要：This paper describes the database development of spoken Hindi Hybrid words. The main focus is on the analysis of spoken Hindi Hybrid Words by using endpoint detection algorithm. The development is done in the robust environment. Male and Female speakers are selected from different states to analyze the acoustical variation in their utterances. Various emotions such as normal, happy, anger and surprise are taken for analysis of speech signal. Endpoint detection algorithm is used for the analysis purpose of various parameters such as Total Duration of time, Number of samples, Root Mean Square value and Mean Power (Intensity) in air of speech signal.
关键词：Spoken Hindi Hybrid Words; Duration; Emotion; Endpoint Detection; Mean Power (Intensity) in air; RMS
