Speech processing in Java-based PC speech commanding application

• Main Authors: T.C., Nguyen, J.L., Tang
• Format: Conference or Workshop Item
• Published: 2007
• Subjects: Q Science (General); QA75 Electronic computers. Computer science
• Online Access: http://eprints.utp.edu.my/151/1/paper.pdf; http://www.scopus.com/inward/record.url?eid=2-s2.0-57949103749&partnerID=40&md5=f304a6705ee95290a41e16ea17e7dd15; http://eprints.utp.edu.my/151/
• Institution: Universiti Teknologi Petronas

Speech Recognition has been an inspirational research for more than four decades. There are many areas in which speech recognition can be applied. The main objective of this research is to enhance human-computer interaction by allowing user the ability to control and command personal computer (PC) with natural language. The main approach used in this project is the template-based recognition. This approach demands the PC to be trained with speech patterns based on some generic spectral parameter sets. These spectral parameter sets will then be stored as templates in a database. The system will perform the recognition process by matching the parameter set of the input speech with the stored templates. The advantage of this pattern recognition is its flexibility in terms of storage and matching process. In addition, its implementation is relatively easier as compared to many other methods. The outcome of this project may contributes to the further development of speech recognition methods and its relevant applications. ©2007 IEEE.