International Research Journal of Engineering and Technology

International Research Journal of Engineering and Technology
(IRJET)
e-ISSN: 2395-0056
Volume: 07 Issue: 01 | Jan 2020
www.irjet.net p-ISSN: 2395-0072
 
 
© 2020, IRJET | Impact Factor value: 7.34 | ISO 9001:2008 Certified Journal
| Page 1204 
and so on to enhanced accuracy. [3] Nowadays, the speech 
signals processing takes important place at the present 
development stage of methods and tools for building 
artificial intelligence systems. Real-time support is a 
common requirement that is proffered to methods of 
analysis and synthesis of speech information. As a result, 
methods of the direction of linear prediction [5, 7] during the 
simulation of speech signals become significantly interesting 
and widely used. The main idea of these methods is to 
represent the signal into a form of autoregression. [4] Any 
undetermined signal is defined as a nonlinear object. But it is 
always possible to select time interval from the signals with 
a given discretization period. Such an interval is called 
quasistationary interval. The quasistationary interval in 
combination with the speech signal quality characteristics 
can be used to build a parametric model of the speech signal.
Audio segmentation and classification have many 
applications. Content-based audio classification and retrieval 
are mostly used in entertainment industry, audio archive 
management, commercial music usage, surveillance, and so 
forth. Nowadays, on the World Wide Web, millions of 
databases are present; for audio searching and indexing 
audio segmentation and classification are used. In 
monitoring broadcast news programs, audio classification is 
used, helping in efficient and accurate navigation through 
broadcast news archives.. 
2. Materials and methods: