Abstract
This paper presents a pruning approach for minimizing the execution time in the pattern matching process during speaker verification. Specifically, our speaker verification system uses mel-frequency cepstral coefficient feature extraction and GMM-based pattern matching techniques. The pruning approach may make the verification decision by considering only a special portion of the testing utterance. Our experimental investigation shows that the pruning approach can reduce the execution time of the pattern matching process by as much as 50% in some verification trials. Together with other optimization strategies, this work enables speaker verification to become feasible in mobile embedded systems.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Leung, C.C., Moon, Y.S.: Effect of Window Size and Shift Period in Mel-warped Cepstral Feature Extraction on GMM-based Speaker Verification. In: Proceedings of the 4th International Conference on Audio- and Video-based Biometric Person Authentication (AVBPA), pp. 438–445 (2003)
Moon, Y.S., Leung, C.C., Pun, K.H.: Fixed-point GMM-based Speaker Verification over Mobile Embedded System. In: Proceedings of ACM Workshop on Biometrics: Method and Applications, pp. 53–57 (2003)
Pellom, B.L., Hansen, J.H.L.: An efficient scoring algorithm for Gaussian mixture model based speaker identification. IEEE Signal Processing Letters 5(11), 281–284 (1998)
Deller, J.R., Proakis, J.G., Hansen, J.H.L.: Discrete-Time Processing of Speech Signals. Macmillan, Basingstoke (1993)
Reynolds, D.A.: Speaker identification and verification using Guassian mixture speaker models. Speech Communications 17, 91–108 (1995)
Carey, M., Parris, E., Bridle, J.: A speaker verification system using alphanets. In: Proceedings of International Conference on Acoustics, Speech, and Signal Processing, pp. 397–400 (1991)
Hidden Markov Model Toolkit – speech recognition research toolkit, http://htk.eng.cam.ac.uk/
Compaq iPAQ H3600 Hardware Documents, http://www.handhelds.org/Compaq/iPAQH3600/
arm-linux-gcc Cross Compiler, ftp://ftp.handhelds.org/pub/linux/arm/toolchain/
Campbell Jr., J.P.: Testing with the YOHO CD-ROM voice verification corpus. In: Proceedings of International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 341–344 (1995)
Rabiner, L., Juang, B.-H.: Fundamentals of Speech Recognition. Prentice Hall, Englewood Cliffs (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Leung, C.C., Moon, Y.S., Meng, H. (2004). A Pruning Approach for GMM-Based Speaker Verification in Mobile Embedded Systems. In: Zhang, D., Jain, A.K. (eds) Biometric Authentication. ICBA 2004. Lecture Notes in Computer Science, vol 3072. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-25948-0_83
Download citation
DOI: https://doi.org/10.1007/978-3-540-25948-0_83
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22146-3
Online ISBN: 978-3-540-25948-0
eBook Packages: Springer Book Archive