Faculty of Information Technology, BUT

Publication Details

Speaker Dependent Frequency Cepstrum Coefficients

ORSÁG Filip. Speaker Dependent Frequency Cepstrum Coefficients. In: Security Technology. CCIS 58. Berlin: Springer Verlag, 2009, pp. 258-264. ISBN 978-3-642-10846-4.
Czech title
Frekvenční kepstrální koeficienty závislé na mluvčím
Type
conference paper
Language
english
Authors
Orság Filip, Ing., Ph.D. (DITS FIT BUT)
Keywords
speaker, recognition, verification, identification, features
Abstract
This paper aims at speaker recognition based upon a novel set of features. Feature extraction is a crucial phase of the speaker recognition process and a proper feature set can influence it dramatically. Many well-known features are not suitable for the speaker recognition as those merge the specifics of the individual voices to make them universal. Therefore, we need features accentuating the individual differences of our voices to be able to recognise speakers reliably. This paper introduces Speaker Dependent Frequency Cepstrum Coefficients (SDFCC) intended for the speaker recognition purposes only. Experimental results prove increase of the reliability in comparison to the well-known features. According to the test results, the SDFCC are very useful and promising for the speaker recognition.
Published
2009
Pages
258-264
Proceedings
Security Technology
Series
CCIS 58
Conference
Security Technology 2009, Jeju Island, KR
ISBN
978-3-642-10846-4
Publisher
Springer Verlag
Place
Berlin, DE
BibTeX
@INPROCEEDINGS{FITPUB8986,
   author = "Filip Ors\'{a}g",
   title = "Speaker Dependent Frequency Cepstrum Coefficients",
   pages = "258--264",
   booktitle = "Security Technology",
   series = "CCIS 58",
   year = 2009,
   location = "Berlin, DE",
   publisher = "Springer Verlag",
   ISBN = "978-3-642-10846-4",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/8986"
}
Back to top