E
Eduardo Lleida
Researcher at University of Zaragoza
Publications - 192
Citations - 2402
Eduardo Lleida is an academic researcher from University of Zaragoza. The author has contributed to research in topics: Speaker recognition & Computer science. The author has an hindex of 23, co-authored 181 publications receiving 2172 citations. Previous affiliations of Eduardo Lleida include Bell Labs & Aalborg University.
Papers
More filters
Journal ArticleDOI
Unsupervised Adaptation of Deep Speech Activity Detection Models to Unseen Domains
TL;DR: Experimental results demonstrate that domain adaptation techniques seeking to minimise the statistical distribution shift provide the most promising results, and Deep CORAL method reports a 13% relative improvement in the original evaluation metric when compared to the unadapted baseline model.
Book ChapterDOI
Evaluation of a New Beam-Search Formant Tracking Algorithm in Noisy Environments
Dayana Ribas González,Jose Lainez,Antonio Miguel,Alfonso Ortega Giménez,Eduardo Lleida,José Ramón Calvo de Lara +5 more
TL;DR: The results show that the beam-search formant tracker have a robust behavior in noisy environments and it is clearly more precise than the rest of compared methods.
Proceedings ArticleDOI
Local projections and support vector based feature selection in speech recognition.
TL;DR: The proposed method combines two techniques to select the feature set, first a realibility metric based on information theory and a support vector set to reduce the errors, so that only the features which incorporate implicit robustness to mismatch are selected.
Journal ArticleDOI
Generalizing AUC Optimization to Multiclass Classification for Audio Segmentation With Limited Training Data
TL;DR: In this paper, an extension to the Area Under the ROC curve (AUC) optimisation framework can be easily applied to an arbitrary number of classes, aiming to overcome the issues derived from training data limitations in deep learning solutions.
Journal ArticleDOI
Wiener Filter and Deep Neural Networks: A Well-Balanced Pair for Speech Enhancement
TL;DR: Experiments show that the use of data-driven learning of the SNR estimator provides robustness to the statistical-based speech estimator algorithm and achieves performance on the state-of-the-art.