Abstract
We present a text-dependent speaker verification system based on Hidden Markov Models. A set of features, based on the temporal duration of context-dependent phonemes, is used in order to distinguish amongst speakers. Our approach was tested using the YOHO corpus; it was found that the HMM-based system achieved an equal error rate (EER) of 0.68% using conventional (acoustic) features and an EER of 0.32% when the time features were combined with the acoustic features. This compares well with state-of-the-art results on the same test, and shows the value of the temporal features for speaker verification. These features may also be useful for other purposes, such as the detection of replay attacks, or for improving the robustness of speaker-verification systems to channel or speaker variations. Our results confirm earlier findings obtained on text-independent speaker recognition [1] and text-dependent speaker verification [2] tasks, and contain a number of suggestions on further possible improvements.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ferrer, L., Bratt, H., Gadde, V.R.R., Kajarekar, S., Shriberg, E., Sönmez, K., Stolcke, A., Venkataraman, A.: Modeling duration patterns for speaker recognition. In: Proceedings of Eurospeech, pp. 784–787 (September 2003)
van Heerden, C.J., Barnard, E.: Using timing information in speaker verification. In: Proceedings of the Symposium of the Pattern Recognition Association of South Africa, pp. 53–57 (December 2005)
Campbell, J.P.: Speaker recognition: A tutorial. Proceedings of the IEEE 85, 1437–1462 (1997)
Martin, A.: Evaluations of Automatic Speaker Classification Systems. In: Müller, C. (ed.) Speaker Classification. Lecture Notes in Computer Science / Artificial Intelligence, vol. 4343, Springer, Heidelberg (2007) (this issue)
Koreman, J., Wu, D., Morris, A.C.: Enhancing Speaker Discrimination at the Feature Level. In: Müller, C. (ed.) Speaker Classification. Lecture Notes in Computer Science / Artificial Intelligence, vol. 4343, Springer, Heidelberg (2007) (this issue)
Campbell, J.: Testing with the YOHO CD-ROM voice verification corpus. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 1, pp. 341–344 (May 1995)
Campbell, J.P., Reynolds, D.A.: Corpora for the evaluation of speaker recognition systems. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 2, pp. 829–832 (March 1999)
Higgens, A., Bahler, L., Porter, J.: Speaker verification using randomized phrase prompting. Digital Signal Processing 1(2), 89–106 (1991)
Reynolds, D.A.: Speaker identification and verification using gaussian mixture speaker models. Speech Communication 17, 91–108 (1995)
Liou, H.-S., Mammone, R.J.: A subword neural tree network approach to text-dependent speaker verification. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 1, pp. 357–360 (May 1995)
Rosenberg, A.E., DeLong, J., Lee, C.-H., Juang, B.-H., Soong, F.K.: The use of cohort normalized scores for speaker verification. In: Proceedings of the International Conference on Spoken Language Processing (ICSLP), vol. 1, pp. 599–602 (October 1992)
Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Moore, G., Odell, J., Ollason, D., Povey, D., Veltchev, V., Woodland, P.: The HTK Book, Cambridge University Engineering Department (2005), http://htk.eng.cam.ac.uk/
Huckvale, M.: How is individuality expressed in voice? An introduction to speech production & description for speaker classification. In: Müller, C. (ed.) Speaker Classification. LNCS/LNAI, vol. 4343, Springer, Heidelberg (2007)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
van Heerden, C.J., Barnard, E. (2007). Durations of Context-Dependent Phonemes: A New Feature in Speaker Verification. In: Müller, C. (eds) Speaker Classification II. Lecture Notes in Computer Science(), vol 4441. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74122-0_9
Download citation
DOI: https://doi.org/10.1007/978-3-540-74122-0_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74121-3
Online ISBN: 978-3-540-74122-0
eBook Packages: Computer ScienceComputer Science (R0)