R
Rubén San-Segundo
Researcher at Technical University of Madrid
Publications - 91
Citations - 1912
Rubén San-Segundo is an academic researcher from Technical University of Madrid. The author has contributed to research in topics: Sign language & Word error rate. The author has an hindex of 20, co-authored 87 publications receiving 1484 citations. Previous affiliations of Rubén San-Segundo include University of Colorado Boulder.
Papers
More filters
A Discriminative Text Categorization Technique for Language Identification built into a PPRLM System
TL;DR: A state-of-the-art language identification system based on a parallel phone recognizer, the same as in PPRLM, but instead of using as phonotactic constraints traditional n-gram language models, a new language model is created using a ranking with the most frequent and discriminative n- grams between languages.
Source Language Categorization for improving a Speech into Sign Language Translation System
Verónica López-Ludeña,Rubén San-Segundo,Syaheerah Lufti,Juan Manuel Lucas-Cuesta,Julián David Echevarry,Beatriz Martínez-González +5 more
TL;DR: This paper describes a categorization module for improving the performance of a Spanish into Spanish Sign Language (LSE) translation system that replaces Spanish words with associated tags and reveals that the BLEU has increased.
Proceedings ArticleDOI
Attention-based word vector prediction with LSTMs and its application to the OOV problem in ASR
Alejandro Coucheiro-Limeres,Fernando Fernández-Martínez,Rubén San-Segundo,Javier Ferreiros-López +3 more
TL;DR: In this paper, the authors proposed three architectures for word vector prediction with LSTMs, which consider both past and future contexts of a word for predicting a vector in an embedded space where its surrounding area is semantically related to the considered word.
Journal ArticleDOI
AMIC: Affective multimedia analytics with inclusive and natural communication
Alfonso Ortega,Eduardo Lleida,Rubén San-Segundo,Javier Ferreiros,Lluís F. Hurtado,Emilio Sanchis,María Inés Torres,Raquel Justo +7 more
TL;DR: This project is focused on advancing, developing and improving speech and language technologies as well as image and video technologies in the analysis of multimedia content adding to this analysis the extraction of affective-emotional information.
Journal ArticleDOI
Robust Biometrics from Motion Wearable Sensors Using a D-vector Approach
TL;DR: The robustness of the proposed d-vector approach for extracting robust biometrics from inertial signals recorded with wearable sensors is demonstrated and the proposed architecture includes two convolutional layers for learning features from the inertial signal spectrum.