期刊名称：International Journal of Soft Computing & Engineering
电子版ISSN：2231-2307
出版年度：2012
卷号：2
期号：3
页码：28-31
出版社：International Journal of Soft Computing & Engineering
摘要：Over the last few years major efforts have been made to develop methods for extracting information from audio-visual media, in order that they may be stored and retrieved in databases automatically. In this work we deal with the characterization of an audio signal, which is a part of a larger audio-visual system. Our goal was first to develop a system for segmentation of the audio signal, and then classify into one of two main categories: speech or music. The basic characteristics are computed in 2sec intervals. The result shows that the estimation of short time energy reflects more effectively the difference in human voice and musical instrument than zero crossing rate and spectrum flux.
关键词：Speech/music;classification;audio;segmentation; zero crossing rate; short time energy; and spectrum;flux.
