Speaker recognition using mel frequency cepstrum
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...
| Main Authors: | , , , , |
|---|---|
| Format: | Book Chapter |
| Language: | English |
| Published: |
IIUM Press
2011
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/21661/ http://irep.iium.edu.my/21661/ http://irep.iium.edu.my/21661/1/Chapter_28.pdf |
| Summary: | 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 |
|---|