Abstract
In some situations the quality of the signals involved in a speaker verification trial is not as good as needed to take a reliable decision. In this work, we use Bayesian networks to model the relations between the speaker verification score, a set of speech quality measures and the trial reliability. We use this model to detect and discard unreliable trials. We present results on the NIST SRE2010 dataset artificially degraded with different types and levels of additive noise and reverberation. We show that a speaker verification system, that is well calibrated for clean speech, produces an unacceptable actual DCF on the degraded dataset. We show how this method can be used to reduce the actual DCF to values lower than 1. We compare results using different quality measures and Bayesian network configurations.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Huggins, M.C., Grieco, J.J.: Confidence metrics for speaker identification. In: 7th ICSLP, Denver, Colorado (2002)
Campbell, W.M., Reynolds, D.A., Campbell, J.P., Brady, K.J.: Estimating and evaluating confidence for forensic speaker recognition. In: ICASSP 2005, vol. 1, pp. 717–720 (2005)
Solewicz, Y., Koppel, M.: Considering Speech Quality in Speaker Verification Fusion. In: Interspeech 2005 (2005)
Richiardi, J., Drygajlo, A., Prodanov, P.: A probabilistic measure of modality reliability in speaker verification. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2005 (2005)
Richiardi, J., Drygajlo, A., Prodanov, P.: Confidence and reliability measures in speaker verification. Journal of the Franklin Institute 343(6), 574–595 (2006)
Richiardi, J., Drygajlo, A., Prodanov, P.: Speaker Verification with Confidence and Reliability Measures. In: Proc. of ICASSP, vol. 1(6), pp. 641–644 (2006)
Nakasone, H., Beck, S.D.: Forensic automatic speaker recognition. In: Odyssey Speaker and Language Recognition Workshop (2001)
Bengio, S., Marcel, C., Marcel, S., Mariethoz, J.: Confidence Measures for Multimodal Identity Verification. Information Fusion 3(4), 267–276 (2002)
Poh, N., Bengio, S.: Improving Fusion with Margin-Derived Confidence in Biometric Authentication Tasks. In: Kanade, T., Jain, A., Ratha, N.K. (eds.) AVBPA 2005. LNCS, vol. 3546, pp. 474–483. Springer, Heidelberg (2005)
Kryszczuk, K., Richiardi, J., Prodanov, P., Drygajlo, A.: Reliability-Based Decision Fusion in Multimodal Biometric Verification Systems. EURASIP Journal on Advances in Signal Processing, 1–10 (2007)
Talkin, D.: A robust algorithm for pitch tracking (RAPT). In: Speech Coding and Synthesis, pp. 495–518 (1995)
Villalba, J., Lleida, E.: Detecting Replay Attacks from Far-Field Recordings on Speaker Verification Systems. In: Vielhauer, C., Dittmann, J., Drygajlo, A., Juul, N.C., Fairhurst, M.C. (eds.) BioID 2011. LNCS, vol. 6583, pp. 274–285. Springer, Heidelberg (2011)
Harriero, A., Ramos, D., Gonzalez-Rodriguez, J., Fierrez, J.: Analysis of the Utility of Classical and Novel Speech Quality Measures for Speaker Verification. In: Tistarelli, M., Nixon, M.S. (eds.) ICB 2009. LNCS, vol. 5558, pp. 434–442. Springer, Heidelberg (2009)
Bishop, C.: Pattern Recognition and Machine Learning. Springer Science+Business Media, LLC (2006)
Hirsch, H.-G., Pearce, D.: The Aurora Experimental Framework for the Performance Evaluation of Speech Recognition Systems under Noisy Conditions. In: 6th International Conference on Spoken Language Processing, ICSLP 2000, pp. 16–19. Citeseer, Beijing (2000)
Hirsch, H.-G.: FaNT - Filtering and Noise Adding Tool (2005)
McGovern, S.: A Model for Room Acoustics (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Villalba, J., Lleida, E., Ortega, A., Miguel, A. (2012). Reliability Estimation of the Speaker Verification Decisions Using Bayesian Networks to Combine Information from Multiple Speech Quality Measures. In: Torre Toledano, D., et al. Advances in Speech and Language Technologies for Iberian Languages. Communications in Computer and Information Science, vol 328. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35292-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-35292-8_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35291-1
Online ISBN: 978-3-642-35292-8
eBook Packages: Computer ScienceComputer Science (R0)