The 2013 speaker recognition evaluation in mobile environment

Abstract

El acceso a la versión del editor puede requerir la suscripción del recurso Access to the published version may require subscription AbstractThis 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.

The 2013 face recognition evaluation in mobile environment

“…Finally, future work will focus on a biometric verification system that fuses scores from face and speaker [4] verification systems.…”

“…Therefore, in table 4 the institutions that provide the source code for their algorithms are highlighted as well. Unfortunately, additionally to the baseline 4 only one participant releases source code 4 for the algorithm.…”

“…Together with the speaker verification evaluation [4], it is the second in an ongoing series of face and speaker recognition evaluations [5]. The evaluation is carried out on the MOBIO database [6], which con- * corresponding author: manuel.guenther@idiap.ch tains videos of talking faces that were captured with mobile devices.…”

Evaluating Automatic Speaker Recognition systems: An overview of the NIST Speaker Recognition Evaluations (1996-2014)

“…Recently, a renewed interest in those systems has been observed, as shown by the MOBIO evaluation (Khoury et al, 2013) for voice access control in mobile environments whose results were presented at the International Conference on Biometrics (ICB) 2013 in Madrid, and in an IN-TERSPEECH 2014 special session entitled "Text-dependent speaker verification with short utterances" which will be focused on "robustness with respect to duration and modeling of lexical information" (Larcher, Aronowitz, Lee, & Kenny, 2014). Interestingly, the organizers have madepubliclyavailabilitytheRSR2015database,including 150 hours of data recorded from 300 speakers in mobile environments, which allow text-dependent system design and evaluation in different configurations, and comparison of results with other systems using the same database (Larcher, Lee, Ma, & Li, 2014).…”

An Evaluation of Bimodal Recognition Systems Based on Voice and Facial Images

“…It was considered the gender in the pairing of both databases as well. For this dataset, the International Conference on Biometrics (ICB-2013) opened a competition in which two evaluation protocols for speaker and face recognition systems were defined [88,89]. In those, an identical partitioning of the database was set on each case, as shown in Table 4 In this work, we used the same partitioning for our experiments, with the difference that we discarded the evaluation set because the probe samples were not labeled, so we only worked with the training and development sets.…”