Abstract
In this paper, the improvements of the speaker verification system, which is used at Department of Cybernetics at University of West Bohemia, are introduced. The paper summarizes our actual pieces of knowledge in the acoustic modeling domain, in the domain of the model creation and in the domain of score normalization based on the universal background models. The constituent components of the state-of-art verification system were modified or replaced by virtue of the actual pieces of knowledge. A set of experiments was performed to evaluate and compare the performance of the improved verification system and the baseline verification system based on HTK-toolkit. The results prove that the improved verification system outperforms the baseline system in both of the reviewed criterions – the equal error rate and the time consumption.
The work was supported by the Ministry of Education of the Czech Republic, project No. MSM 235200004, and by the Grant Agency of the Czech Republic, project No. 102/05/0278.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Vaněk, J., Padrta, A.: Optimization of features for robust speaker recognition. In: Speech processing. Prague: Academy of Sciences of the Czech Republic, pp. 140–147 (2004) ISBN 80-86269-11-6
Vaněk, J., Padrta, A., Radová, V.: An algorithm for speaker model training. In: Eurospeech 2005, Lisabon (2005) (submitted)
Padrta, A., Radová, V.: On the background model construction for speaker verification using GMM. In: TSD 2004 - Text, speech and dialogue, pp. 425–432. Springer, Berlin (2004) ISBN 3-540-23049-1. ISSN 0302-9743
Prcín, M., Müller, L., Šmídl, L.: Statistical Based Speech/Non-speech Detector with Heuristic Feature Set. In: SCI 2002 –World Multiconference on Systemics, Cybernetics and Informatics Orlando FL-USA, pp. 264–269 (2002)
Young, S., et al.: The HTK book, Cambridge (1995)
Reynolds, D.A.: Speaker identification and verification using Gaussian mixture speaker models. Speech Communication 17, 91–108 (1995)
Zilca, R.D., Bistricz, Y.: Distance-Based GaussianMixture Model for Speaker Recognition over the Telephone. In: ISCLP 2000, pp. 1001–1003 (2000)
Radová, V., Psutka, J.: UWB S01 Corpus – A Czech Read-Speech Corpus. In: Proc. ICSLP 2000, Beijing, China, pp. 732–735 (2000)
Campbell, J.P.: Testing with the YOHO CD-ROM voice verification corpus. In: ICASSP 1995 (1995)
Campbell Jr., J.P., Reynolds, D.A.: Corpora for the Evaluation of Speaker Recognition Systems. In: ICASSP 1999 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Padrta, A., Vaněk, J. (2005). Introduction of Improved UWB Speaker Verification System. In: Matoušek, V., Mautner, P., Pavelka, T. (eds) Text, Speech and Dialogue. TSD 2005. Lecture Notes in Computer Science(), vol 3658. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11551874_47
Download citation
DOI: https://doi.org/10.1007/11551874_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28789-6
Online ISBN: 978-3-540-31817-0
eBook Packages: Computer ScienceComputer Science (R0)