Smart computers : can you recognise these sounds?

• Main Author: Tan, Li Qing
• Other Authors: Kong Andy Wai Hoong
• Format: Final Year Project
• Language: English
• Published: 2015
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
• Online Access: http://hdl.handle.net/10356/63566
• Institution: Nanyang Technological University

Sound recognition technology has been around for quite some time but is not widely recognised by day to day IT users. It even exists within the latest mobile phones on the market with technology such as Apple's Siri and Samsung's S voice. This report will explore the use of sound recognition and how it may be put in certain places or situations whereby it will greatly benefit law enforcers or road users. The process of how experiments are conducted and the methodology used in setting up the experiment will be explained in depth. The sound classification process will be trained using the Support Vector Machine and thereafter be tested in real time scenarios to see how accurately the program can predict a particular sound. As experiment and sample data were collected in an enclosed room, the test is only accurate if conducted in an environment with similar ambience. Results may differ if the system is taken out to a different environment for testing.