Publication Details
The 2013 Speaker Recognition Evaluation in Mobile Environment
Vesnicer Boštjan (ALPINEON)
Franco-Pedroso Javier (UAM)
Diez Sánchez Mireia (UPV)
Cipr Tomáš, Ing. (DCGM FIT BUT)
Schwarz Petr, Ing., Ph.D. (DCGM FIT BUT)
van Leeuwen David (TNO)
Petrovska-Delacretaz Dijana, Dr. (unifr)
Matějka Pavel, Ing., Ph.D. (DCGM FIT BUT)
Rodriguez-Fuentes Luis J. (EHU)
Chollet Gerard, Dr. (GET/ENST)
and others
speaker recognition, mobile environment, evaluation
This paper presents the results of the participants to the evaluation on speaker verification in mobile environment.
This paper evaluates the performance of the twelve primary systems submitted to the evaluation on speaker verification in the context of a mobile environment using the MOBIO database. The mobile environment provides a challenging and realistic test-bed for current state-of-the-art speaker verification techniques. Results in terms of equal error rate (EER), half total error rate (HTER) and detection error trade-off (DET) confirm that the best performing systems are based on total variability modeling, and are the fusion of several sub-systems. Nevertheless, the good old UBM-GMM based systems are still competitive. The results also show that the use of additional data for training as well as gender-dependent features can be helpful.
@INPROCEEDINGS{FITPUB10529, author = "S. Elie Khoury and Bo\v{s}tjan Vesnicer and Javier Franco-Pedroso and Mireia S\'{a}nchez Diez and Tom\'{a}\v{s} Cipr and Petr Schwarz and David Leeuwen van and Dijana Petrovska-Delacretaz and Pavel Mat\v{e}jka and J. Luis Rodriguez-Fuentes and Gerard Chollet and Sebastien Marcel and et al.", title = "The 2013 Speaker Recognition Evaluation in Mobile Environment", pages = "1--8", booktitle = "Proceedings of Biometrics (ICB), 2013 International Conference on", year = 2013, location = "Madrid, ES", publisher = "IEEE Biometric Council", ISBN = "978-1-4799-0310-8", doi = "10.1109/ICB.2013.6613025", language = "english", url = "https://www.fit.vut.cz/research/publication/10529" }