Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
MEKYSKA, J. FAÚNDEZ ZANUY, M. FABREGAS, J. SMÉKAL, Z.
Originální název
Fast and Efficient Approaches in Text-dependent Speaker Recognition Systems
Typ
článek v časopise - ostatní, Jost
Jazyk
angličtina
Originální abstrakt
Although text-dependent speaker recognition systems are not so intensively developed as text-independent ones, there are still many applications, where the text dependency is necessary. This is for example a case of biometric systems. With the increasing computational burden and decreasing price of memories it is possible to implement new and sophisticated algorithms that rapidly increase the accuracy of these systems. But there are still some applications, where fast, simple and efficient approaches are necessary. This work introduces new methods of the text-dependent speaker recognition based on voice imprint and classifiers suitable for the processing of this feature vector. It is shown, that using combination of voice imprint and classifier based on fractional distances, it is possible to reach the successful detection rate equal to 96.94 % and 82.29 % in case of microphone mismatch. Speaking about equal error rate, system reached 4.08 % and 10.94 % considering microphone mismatch. It is also shown that voice imprint can approximately 30 times decrease the memory requirements.
Klíčová slova
text-dependent speaker recognition, multi-section vector quantization
Autoři
MEKYSKA, J.; FAÚNDEZ ZANUY, M.; FABREGAS, J.; SMÉKAL, Z.
Rok RIV
2011
Vydáno
1. 4. 2011
ISSN
1213-1539
Periodikum
Elektrorevue - Internetový časopis (http://www.elektrorevue.cz)
Ročník
2
Číslo
1
Stát
Česká republika
Strany od
Strany do
6
Strany počet
BibTex
@article{BUT74440, author="Jiří {Mekyska} and Marcos {Faúndez Zanuy} and Joan {Fabregas} and Zdeněk {Smékal}", title="Fast and Efficient Approaches in Text-dependent Speaker Recognition Systems", journal="Elektrorevue - Internetový časopis (http://www.elektrorevue.cz)", year="2011", volume="2", number="1", pages="1--6", issn="1213-1539" }