A5021983834- Speech Recognition and Synthesis
- Handwritten Text Recognition Techniques
- Biometric Identification and Security
- User Authentication and Security Systems
- Natural Language Processing Techniques
- Phonetics and Phonology Research
- Speech and Audio Processing
- Teaching and Learning Programming
- Music and Audio Processing
- Speech and dialogue systems
- Text and Document Classification Technologies
- Imbalanced Data Classification Techniques
- Algorithms and Data Compression
- Advanced Image and Video Retrieval Techniques
- Gait Recognition and Analysis
- Educational Games and Gamification
- Biomedical Text Mining and Ontologies
- Experimental Learning in Engineering
- Hand Gesture Recognition Systems
- Anomaly Detection Techniques and Applications
- Literacy and Educational Practices
- Innovative Teaching Methods
- Linguistic Studies and Language Acquisition
- Retinal Diseases and Treatments
- Assistive Technology in Communication and Mobility
Universidad de Valladolid
2011-2025
Centro Tecnológico de Investigación, Desarrollo e Innovación en tecnologías de la Información y las Comunicaciones (TIC)
2009
The current need for large multimodal databases to evaluate automatic biometric recognition systems has motivated the development of MCYT bimodal database. main purpose been consider a scale population, with statistical significance, in real procedure, and including several sources variability that can be found environments. acquisition process, contents availability single-session baseline corpus are fully described. Some experiments showing consistency data through different sites...
ABSTRACT Higher Education programming courses usually present high levels of student failure and drop‐out rates. Given this context, the use educational video games is proposed as a strategy to increase students' motivation engagement, thus helping diminish such However, there lack empirical studies examining effects, especially when they are outside formal curriculum (i.e., extracurricular) students enrolled in different bachelors. This paper presents cross‐sectional study following...
In this paper, we present the main results of BioSecure Signature Evaluation Campaign (ESRA'2011). The objective ESRA'2011 is to evaluate through two different tasks resistance online signature systems skilled forgeries categorized automatically according their quality. Task 1 aims at studying with only coordinate time functions influence acquisition conditions (digitizing tablet vs. PDA) on systems' performance. Data Sets DS2 and DS3 make possible, since they contain data from same 382...
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 the intrinsic difficulty classification. We focus on problem, identifying eight types pitch accent tones, nine boundary five indices. complex multi-class problem is divided into several simpler problems, by means pairwise coupling. propose to combine...
In this study, an application that allows a mobile phone to be used as biometric-capture device is shown. The main contribution of our proposal capture, and later recognition, can performed during standard web session, using the same architecture in personal computer (PC), thus allowing multiplatform (PC, digital assistant (PDA), phone, etc.) biometric access. review, which from both academic commercial point view, biometry state art shows other related works, capture recognition either...
In this work, a novel Window Score Fusion post-processing technique for biometric gait recognition is proposed and successfully tested. We show that the use of allows rates to be greatly improved, independently configuration previous stages system. For this, strict evaluation protocol has been followed, using database composed data acquired from 38 subjects by means commercial smartwatch in two different sessions. A cross-session test (where training testing were days) was performed....
This paper deals with the problem of training an Artificial Neural Network (ANN) when data sets are very imbalanced. Most learning algorithms, including ANN, designed for well-balanced and do not work properly on imbalanced ones. Of approaches proposed dealing this problem, we interested in re-sampling ones, since they algorithm-independent. We have recently a new under-sampling technique two-class called Non-Target Incremental Learning (NTIL), which has shown good performance SVM, improving...
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Contribution:</i> A successful activity based on the scavenger hunt (SH) game is presented here. Although "serious game" in education now seems synonymous with videogame, effectiveness of hands-on traditional games to increase student performance that, besides, they also like defended and proved. The proposal not focused, as usual, a single aspect educational environment, but integrating...
Score Normalization is a usual technique in pattern recognition to standardize the classifier output ranges so as to, for example, fuse these outputs. The use of score normalization biometric very important part system, specially those based on behavioral traits, such written signature or voice, conditioning final system performance. Then, many works can be found that focus problem. A successful new approach client threshold prediction, Multiple Linear Prediction, has been presented recent...