Speaker Verification
| Art der Publikation: | Artikel in Sammelband |
| Zitat: | henn08:speak |
| Buchtitel: | Biometrics And Human Identity |
| Kapitel: | Speaker Verification |
| Jahr: | 2008 |
| Verlag: | Grada |
| ISBN: | 978-80-247-2365-5 |
| Abriss: | Speaking is the most natural mean of communication between humans. Driven by a great deal of potential applications in human-machine interaction, systems have been developed to automatically extract the different pieces of information conveyed in the speech signal. There are three ma jor tasks. In speech recognition tasks, the automatic system aims at discovering the sequence of words forming the spoken message. In language recognition tasks, the system attempts to identify the language used in a given piece of speech signal. Finally, speaker recognition systems aim to discover information about the identity of the speaker. Speaker recognition finds applications in many different areas such as access control, transaction authentication, law enforcement, speech data management and personalization. As for other biometric technologies the prime motivation of speaker recognition is to achieve a more usable and reliable personal identification than by using artifacts such as keys, badges, magnetic cards or memorized passwords. Interestingly, speaker recognition is one of the few biometric approach which is not based on image processing. Speaker recognition systems are often said to be performance-based since the user has to produce a sequence of sound. This is also a ma jor difference with other passive biometrics for which the cooperation of the authenticated person is not requested, such as for fingerprints, iris or face recognition systems. Speaker recognition technologies are often ranked as less accurate than other biometric technologies such as finger print or iris scan. However, there are two main factors that make voice a compelling biometric. First, there is a proliferation of automated telephony services for which speaker recognition can be directly applied. Telephone handsets are indeed available basically everywhere and provide the required sensors for the speech signal. Second, talking is a very natural gesture, often considered as lowly intrusive by users as no physical contact is requested. These two factors, added to the recent scientific progresses, made voice biometric converge into a mature technology. Commercial products offering voice biometric are now available from different vendors. However, many technical and non-technical issues, discussed later in this chapter, still remain open and need to be tackled. |
| Schlagworte: | Biometrics, machine learning, Speaker Verification |
| Autoren | |
| Herausgeber | |
| Hinzugefügt von: | [] |
| Gesamtbewertung: | 0 |
|
Anhänge
|
|
|
|
|
Notizen
|
|
|
|
|
|
Themen
|
|
|
|
|
