Automatic Cross-Biometric Footstep Database Labelling Using Speaker Recognition
The often daunting task of collecting and manually labelling biometric databases can be a barrier to research. This is especially true for a new or non-established biometric such as footsteps. The availability of very large data sets often plays a role in the research of complex modelling and normalisation algorithms and so an automatic, semi-unsupervised approach to reduce the cost of manual labelling is potentially of immense value.
This paper proposes a novel, iterative and adaptive approach to the automatic labelling of what is thought to be the first large scale footstep database (more than 10,000 examples across 127 persons). The procedure involves the simultaneous collection of a spoken, speaker-dependent password which is used to label the footstep data automatically via a pre-trained speaker recognition system. Subsets of labels are manually checked by listening to the particular password utterance, or viewing the associated talking face; both are recorded with the same time stamp as the footstep sequence.
Experiments to assess the resulting label accuracy, based on manually labelled subsets, suggest that the accuracy of the automatic labelling is better than 0.1%, and thus sufficient to assess a biometric such as footsteps, which is anticipated to have a much higher error rate.
KeywordsAutomatic database labelling speaker verification score normalisation footstep biometric multimodal biometrics
- 1.Doddington, G.R., Przybocki, M.A., Martin, A.F., Reynolds, D.A.: The NIST speaker recognition evaluation: Overview methodology, systems, results, perspective. Speech Communication 31, 225–254 (2000)Google Scholar
- 2.Toledano, D.T., Esteve-Elizande, C., Gonzalez-Rodriguez, J., Fernandez-Pozo, R., Hernandez-Gomez, L.: Phoneme and Sub-Phoneme T-Normalization for Text-Dependent Speaker Recognition. In: Proc. IEEE Speaker and Language Recognition Workshop (Odyssey) (2008)Google Scholar
- 3.Vera-Rodriguez, R., Lewis, R.P., Mason, J.S.D., Evans, N.W.D.: A Large Scale Footsteps Database for Biometric Sutdies Created using Cross-Biometrics for Labelling. In: Proc. 10th IEEE International Conference on Control, Automation, Robotics and Vision, ICARCV, Vietnam (2008)Google Scholar
- 4.Reynolds, D.A., Quatieri, T.F., Dunn, R.: Speaker Verification Using Adapted Gaussian Mixture Models. Digital Signal Processing 10(1-3), 19–41 (2000)Google Scholar
- 5.Bonastre, J.-F., Scheffer, N., Fredouille, C., Matrouf, D.: NIST 2004 Speaker Recognition Evaluation Campaign: New LIA Speaker Detection Platform Based on ALIZE Toolkit. In: Proc. NIST SRE 2004 Workshop, Spain (2004)Google Scholar
- 6.Fauve, B., Evans, N.W.D., Mason, J.S.D.: Improving the Performance of Text-Independent Short Duration GMM and SVM Based Speaker Verification. In: Proc. Odyssey: the Speaker and Language Recognition Workshop (2008)Google Scholar
- 7.Fauve, B., Bredin, H., Karam, W., Verdet, F., Mayoue, A., Chollet, G., Hennerbert, J., Lewis, R., Mason, J., Mokbel, C., Petrovska, D.: Some Results From The Biosecure Talking Face Evaluation Campaign. In: Proc. ICASSP (2008)Google Scholar
- 8.Auckenthaler, R., Carey, M.J., Lloyd-Thomas, H.: Score normalisation for text-independent speaker verification system. Digital Signal Processing (DSP), a review journal - Special issue on NIST 1999 Speaker Recognition Workshop 10(1-3), 42–54 (2000)Google Scholar
- 9.Navrati, J., Ramaswamy, G.N.: The awe and mystery of T-Norm. In: Proc. Eurospeech, Geneva, pp. 2009–2012 (2003)Google Scholar
- 10.Li, K.P., Porter, J.E.: Normalizations and selection of speech segments for speaker Recognition Scoring. In: Proc. ICASSP, pp. 595–598 (1988)Google Scholar
- 11.Zhang, S., Zheng, R., Xu, A.: A Comparative Study of Feature and Score Normalization for Speaker Verification. In: Proc. IEEE Odyssey Speaker and Language Recognition Workshop, pp. 531–538 (2005)Google Scholar