The use of Group delay features of linear prediction model for speaker recognition

Informatica

Volumn 21, Issue 1, 2010, Pages 1-12

  Bastys, Algirdas ^a   Kisel, Andrej ^a   Šalna, Bernardas ^b  

^a VILNIUS UNIVERSITY   (Lithuania)

^b Lithuanian Forensic Expertise Institute   (Lithuania)

Author keywords

Features; Group delay; Information theory; Linear prediction model; Similarity metric; Speaker recognition

Indexed keywords

EID: 77949801131     PISSN: 08684952     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (20)

1. Alsteris, L.D., Paliwal, K.K. (2007). Short-time phase spectrum in speech processing: A review and some experimental results. Digital Signal Processing: A Review Journal, 17, 578-616. ELRA-S0050 Russian speech database (STC). http://www.linguistlist.org/issues/9/9-891.html.
2. Gambier-Langeveld, T. (2005). NFD, speaker recognition fake case evaluation. In: 8thMeeting of ENFSI Expert Working Group for Forensic Speech and Audio Analysis. Netherlands Forensic Institute.
3. Itakura, F., Saito, S. (1968). Analysis synthesis telephony based upon the maximum likelihoood method. In: Kohasi, Y. (Ed.), Reports on 6th Int. Cong. Acoust.. Tokyo. C-5-5, C17-20.
4. Jinhai, C., Gangji, J., Lihe, Z. (1993). New method for extracting speech formants using LPC phase spectrum. Electronic letters, 29(24), 2081-2082.
5. Kamarauskas, J. (2008). Speaker recognition using aussian mizture model. J. Electronics and Electrical Enginiering, 5(85), 29-32.
6. Kisel, A., Kochetkov, A., Kranauskas, J. (2008). Fingerprint minutiae matching without global alignment using local structures. Informatica, 19(1), 31-44.
7. Lipeika, A., Lipeikiene, J. (1995). Speaker identification using vector quantization. Informatica, 6(2), 167-180.
8. Lipeika, A., Lipeikiene, J. (1999). Speaker recognition based on the use of vocal tract and residue signal LPC parameters. Informatica, 10(4), 377-388.
9. MackKay, D.J.C. (2003). Information Theory, Inference, and Learning Algorithms. Cambridge University Press.
10. Murthy, H.A., Yeganarayana, B. (1991). Speech processing using group delay functions. Signal Processing, 22, 259-267.
11. Reynold, D.A., Rose, R.C. (1995). Robust text-independent speaker identification using Gaussian mixture speakers models. IEEE Transactions on Speech and Audio Processing, 3(1), 72-83.
12. Ribaric, S., Fratric, I., Kis, K. (2008). A novel biometric personal verification system based on the combination of palmprints and faces. Informatica, 19(1), 81-100.
13. Šalna, B., Kamarauskas, J. (2008). Voice biometrics - Evaluation of effectiveness of different methods in speaker recognition. In: Proc. of IEEE Workshop on Bio-inspired Signal and Image Processing. Warshaw, pp. 1-6.
14. Strube, H.W. (1980). Linear prediction on a warped frequency scale. J. Acoust. Soc. Am., 68(4), 1071-1076.
15. Struc, V., Pavesic, N. (2009). Gabor-based kernel partial-least-squares discrimination features for face recognition. Informatica, 20(1), 115-138.
16. Thiruvaran, T., Ambikairajah, E., Epps, J. (2007). Group delay features for speaker recognition. In: Proc. Information, Communications & Signal Processing. Singapore, pp. 1546-1550.
17. Yu A.-T., Wang H.-Ch. (2003). Channel effect compensation in LSF domain. EURASIP Journal on Applied Signal Processing, 9, 922-929.
18. A. Bastys finished Lomonosov State University in 1980, PhD doctor of mathematics in 1983. He is assitent professor of Faculty of Mathematics and Informatics of Vilnius University. His research interests include wavelets, harmonic analysis, biometrics.
19. A. Kisel received his BS and MS degree in computer science from Vilnius University, Lithuania in 2003 and 2005 respectively. He is currently a PhD student in Vilnius University. His research interests include biometric algorithms, image processing and synthetic fingerprint generation. From 2002 he is a research scientist at "Neurotechnology".
20. B. Šalna in 1977 graduated from Radio-Technical Faculty of Kaunas Polytechnic University and got the qualification of a radio engineer. In 1977 he started working at Vilnius University. In 1990 he defended a thesis for a degree of doctor in engineering science "The creation and research of language signal processing methods based on linear prognosis". Since 1991 he has been the head of Phonoscope Expertise Department of the Lithuanian Forensic Expertise Institute as well as the lecturer of the Criminalities Department of Mykolas Romeris University. His main scientific interests: criminology research of speech, voice and acoustical signals and their record means, speech signals analysis, the methods of the identification of a person according to his voice, biometrics