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 state-of-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.

A novel algorithm based on classical cepstrum calculation followed by dynamic programming is presented in this paper. The algorithm has been evaluated with a 60-minutes database containing 60 speakers and different recording conditions and environments. A second reference database has also been used. In addition, the performance of four popular PDA algorithms has been evaluated with the same databases. The results prove the good performance of the described algorithm in noisy conditions. Furthermore, the paper is a first initiative to perform an evaluation of widely used PDA algorithms over an extensive and realistic database.

The aim of this article was to present a new tool for doing dialectometry. The program, called ‘DiaTech’, incorporates features of previous programs, especially features of the VDM program created under the direction of H. Goebl. Its main goal is to motivate dialectology studies and dialectologists by providing a new comfortable and efficient tool. With regard to the linguistic features of the program, the most novel feature of ‘DiaTech’ is its ability to manage ‘multiple responses’, that is, for each question, the dialectologist has the option to record more than one item. As far as its basic technological features are concerned, the ‘DiaTech’ program can be used with different platforms; it has an interface in different languages. Regarding statistical procedures, the DiaTech program gives access to a wide variety of distances, including those that are most typically used in dialectometry for bidimensional and multivariate analyses (cluster, correlation, etc.). In addition, the program makes use of different algorithms for visualization and classification. Finally, it provides the necessary tools to create different types of maps with a polygonized background: question by question maps (as in a linguistic atlas), identity maps, honeycomb maps, synopsis of skewness, standard deviation, dendrogramic maps, correlation maps, etc.