Speaker recognition using mel frequency cepstrum

• Main Authors: Khalifa, Othman Omran, Khan, Sheroz, Islam, Md. Rafiqul, Faizal, M., Dol, D.
• Format: Book Chapter
• Language: English
• Published: IIUM Press 2011
• Subjects: TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices
• Online Access: http://irep.iium.edu.my/21661/1/Chapter_28.pdf; http://irep.iium.edu.my/21661/; http://rms.research.iium.edu.my/bookstore/default.aspx
• Institution: Universiti Islam Antarabangsa Malaysia

Automatic speaker recognition is the use of a machine (i.e. software or hardware) to recognize a person from a spoken phrase. This is done by identifying characteristic acoustic features of their voice which is unique. This makes it possible to use the speaker's voice to verify their identity and can be used to control access to services such as voice dialing, banking by telephone, database access service, security control for confidential information area and remote access to computers. Basically prior to a verification or identification session, users that are authorized to use the system will need to undergo enrollment session, where they provide speech samples that will be processed and stored in the database in order to be used later during the identification process. Here only certain important features that are unique to individuals are extracted while other redundancies are discarded