A new multimodal biometric database, acquired in the framework of the BiosecurID project, is presented together with the description of the acquisition setup and protocol. The database includes eight unimodal biometric traits, namely: speech, iris, face (still images, videos of talking faces), handwritten signature and handwritten text (on-line dynamic signals, off-line scanned images), fingerprints (acquired with two different sensors), hand (palmprint, contour-geometry) and keystroking. The database comprises 400 subjects and presents features such as: realistic acquisition scenario, balanced gender and population distributions, availability of information about particular demographic groups (age, gender, handedness), acquisition of replay attacks for speech and keystroking, skilled forgeries for signatures, and compatibility with other existing databases. All these characteristics make it very useful in research and development of unimodal and multimodal biometric systems.
Pervasive devices interacting in open and dynamicspaces with each others require a mechanism that allows them acting autonomously in a secure way and protecting their resources. Trust is fundamental to establish communication with other users, because the identity is often uncertain and on one's own does not provide trust information, for instance, could an unknown user be trustworthy? Nowadays, these devices have a so limited security support. So, we propose a simple trust management model to enhance such support, allowing them interact in ad hoc networks and peer-to-peer applications in a secure way. In this paper, our main contribution is a mathematical and a probabilistic model, as well as demonstrating the model feasibility, since it has been assessed through the prototype implementation, which has been tested in a Pocket PC.
Chylous fistula is a serious complication of neck surgery. The aim of this study was to analyse the incidence, treatment and evolution of chylous fistula in neck dissection. We conducted a retrospective study of 304 patients, 295 (97.03%) men and nine (2.97%) women. Ages ranged from 24 to 80 years (mean = 59.28 years, SD = 6.02) and they had all undergone neck dissection. Chylous fistula occurred in four cases (1.31%). Incidence was 1.83% in laryngeal cancer and 2.7% in oral cavity and oropharyngeal cancer. No statistically significant correlation was found between tumoral stage and fistula occurrence. Radiotherapy prior to surgery was a risk factor although the association was not statistically significant. The incidence rates for radical and functional neck dissection were 3.3% and 0.46%, respectively, statistically significant (P = 0.042). The fistulas were located on the left side in all cases. One of the four patients required surgical intervention and another one died. The occurrence of chylous fistula increased significantly the length of hospital stay (P = 0.01). Chylous fistulas appear on the left side, radiotherapy prior to surgery is a risk factor and there is not correlation with tumoral stage. Chylous fistulas are significantly more common in radical than in functional dissections and increase significantly the length of hospital stay.
In the field of speaker verification (SV) it is nowadays feasible and relatively easy to create a synthetic voice to deceive a speech driven biometric access system. This paper presents a synthetic speech detector that can be connected at the front-end or at the back-end of a standard SV system, and that will protect it from spoofing attacks coming from stateof-the-art statistical Text to Speech (TTS) systems. The system described is a Gaussian Mixture Model (GMM) based binary classifier that uses natural and copy-synthesized signals obtained from the Wall Street Journal database to train the system models. Three different state-of-the-art vocoders are chosen and modeled using two sets of acoustic parameters: 1) relative phase shift and 2) canonical Mel Frequency Cepstral Coefficients (MFCC) parameters, as baseline. The vocoder dependency of the system and multivocoder modeling features are thoroughly studied. Additional phase-aware vocoders are also tested. Several experiments are carried out, showing that the phase-based parameters perform better and are able to cope with new unknown attacks. The final evaluations, testing synthetic TTS signals obtained from the Blizzard challenge, validate our proposal. IndexTerms-BIO-MODA-VOI, voice biometrics, anti-spoofing, phase information, synthetic speech detection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.