Valentín Cardeñoso-Payo

BiosecurID: a multimodal biometric database

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.

Practical On-Line Signature Verification

A new DTW-based on-line signature verification system is presented and evaluated. The system is specially designed to operate under realistic conditions, it needs only a small number of genuine signatures to operate and it can be deployed in almost any signature capable capture device. Optimal features sets have been obtained experimentally, in order to adapt the system to environments with different levels of security. The system has been evaluated using four on-line signature databases (MCYT, SVC2004, BIOMET and MyIDEA) and its performance is among the best systems reported in the state of the art. Average EERs over these databases lay between 0.41% and 2.16% for random and skilled forgeries respectively.

Applying data mining techniques to corpus based prosodic modeling

This article presents MEMOInt, a methodology to automatically extract the intonation patterns which characterize a given corpus, with applications in text-to-speech systems. Easy to understand information about the form of the characteristic patterns found in the corpus can be obtained from MEMOint in a way which allows easy comparison with other proposals. A visual representation of the relationship between the set of prosodic features which could have been selected to label the corpus and the intonation contour patterns is also easy to obtain. The particular function-form correspondence associated to the given corpus is represented by means of a list of dictionaries of classes of parameterized F0 patterns, where the access key is given by a sequence of prosodic features. MEMOInt can also be used to obtain valuable information about the relative impact of the use of different parameterization techniques of F0 contours or of different types of intonation units and information about the relevance of different prosodic features. The methodology has been specifically designed to provide a successful strategy to solve the data sparseness problem which usually affects corpora as a consequence of the inherent high variability of the intonation phenomenon.

Improving Automatic Classification of Prosodic Events by Pairwise Coupling

This paper presents a system that automatically labels tones and break indices (ToBI) events. The detection (binary classification) of prosodic events has received significantly more attention from researchers than its classification because of the intrinsic difficulty of classification. We focus on the classification problem, identifying eight types of pitch accent tones, nine types of boundary tones and five types of break indices. The complex multi-class classification problem is divided into several simpler problems, by means of pairwise coupling. We propose to combine two-class classifiers to achieve the multi-class classification because two-class problems provide high accuracy results. Furthermore, complementarity between artificial neural networks and decision trees classifiers has been exploited to improve the final system, combining their outputs using a fusion method. This proposal, together with the adequate feature extraction that includes the use of features such as the Tilt and Bézier parameters, allows us to achieve a total classification accuracy of 70.8% for pitch accents, 84.2% for boundary tones and 74.6% for break indices, on the Boston University Radio News Corpus. The analysis of the misclassified samples shows that the types of mistakes that the system makes do not differ significantly from the common confusions that are observed in manual ToBI inter-transcriber tests.

A fuzzy classifier to deal with similarity between labels on automatic prosodic labeling

This paper presents an original approach to automatic prosodic labeling. Fuzzy logic techniques are used for representing situations of high uncertainty with respect to the category to be assigned to a given prosodic unit. The Fuzzy Integer technique is used to combine the output of different base classifiers. The resulting fuzzy classifier benefits from the different capabilities of the base classifiers for identifying different types of prosodic events. At the same time, the fuzzy classifier identifies the events that are potentially more difficult to be labeled. The classifier has been applied to the identification of ToBI pitch accents. The state of the art on pitch accent multiclass classification reports around 70% accuracy rate. In this paper we describe a fuzzy classifier which assigns more than one label in confusing situations. We show that the pairs of labels that appear in these uncertain situations are consistent with the most confused pairs of labels reported in manual prosodic labeling experiments. Our fuzzy classifier obtains a soft classification rate of 81.8%, which supports the potential of the proposed system for computer assisted prosodic labeling.

SPC-XML: a structured representation for nested-parallel programming languages

Nested-parallelism programming models, where the task graph associated to a computation is series-parallel, present good analysis properties that can be exploited for scheduling, cost estimation or automatic mapping to different architectures. In this paper we present an XML intermediate representation for nested-parallel programming languages from which the application task-graph can be easily derived. We introduce some design principles oriented to allow the compiler to exploit information about the task synchronization structure, automatically determine implicit communication structures, apply different scheduling policies, and generate lower-level code using different models or communication tools. Results obtained for simple applications, using an extensible prototype compiler framework, show how this flexible approach can lead to portable and efficient implementations.

Building Voice Applications from Web Content

Using voice to access on-line information from the web would be really useful, because of the proliferation of mobile devices which allow Internet access anytime and anywhere. However, vocal interface is sequential and not persistent, and thus, we have to restructure the information in order to achieve an efficient and natural way of interaction. Our proposal is based on converting original web contents into VoiceXML dialogues, using VoiceXML templates and extraction rules written in XSLT. Our system has two main components: a development tool to build voice applications and a transcoding server to access them. We have identified five typical HTML patterns and designed a way to browse them using voice.

From HTML to VoiceXML: A First Approach

In this work, we discuss the construction process of the voice portal counterpart of a departmental web site. VoiceXML has been used as the dialogue modelling language. A prototypical system has been built using our own VoiceXML interpreter, which easily integrates different implementation platforms. A general discussion of VoiceXML advantages and disadvantages is reported and a simple startup procedure is proposed as a means to build voice portals starting from legacy web sites.

A preliminary nested-parallel framework to efficiently implement scientific applications

Nested-parallel programming models, where the task graph associated to a computation is series-parallel, present good analysis properties that can be exploited for scheduling, cost estimation or automatic mapping to different architectures. In this work we present a preliminary framework approach to exploit some of these advantages. In our framework we reconstruct an application task graph from a high-level specification, where no scheduling or communication details are yet expressed. The obtained synchronization structure determines which mapping modules or back-ends are used to port the application to an specific platform. The first results obtained with our prototype show that even simple balancing techniques for irregular scientific applications may be easily integrated in this nested-parallel framework, to obtain efficient implementations from high-level and portable specifications. Topic: Parallel and Distributed Computing.

Analysis of inconsistencies in cross-lingual automatic ToBI tonal accent labeling

This paper presents an experimental study on how corpus-based automatic prosodic information labeling can be transferred from a source language to a different target language. Tone accent identification models trained for Spanish, using the ESMA corpus, are used to automatically assign tonal accent ToBI labels on the (English) Boston Radio news corpus, and vice versa. Using just local raw prosodic acoustic features, we got about 75% correct annotation rates, which provides a good starting point to speed up automatic prosodic labeling of new unlabeled corpora. Despite the different ranges and relevance of inter corpora acoustic input features, the contrasting of the results with respect to manual labeling profiles indicate the potential capabilities of the procedure.