Effective background data selection for SVM-based speaker recognition with unseen test environments: more is not always better

[Budgetary blues: more is not always better].

Después de años de un continuado crecimiento muy por encima el de nuestro producto interior bruto, el gasto sanitario empieza mostrar inequívocamente su frenada. Las alegrías de su pasado umento se tornan en tristeza y decaimiento, con una verosímil endencia a ir a menos. Es comprensible que la situación no suscite legría, pero no deja de extrañar la generalizada preocupación por l «mal color» ...

Is more always better

Is more always better? We address this question in the context of bibliometric indices that aim to assess the scientific impact of individual researchers by counting their number of highly cited publications. We propose a simple model in which the number of citations of a publication depends not only on the scientific impact of the publication but also on other ‘random’ factors. Our model indic...

Improved Svm Speaker Verification through Data-driven Background Dataset Selection

The problem of background dataset selection in SVM-based speaker verification is addressed through the proposal of a new datadriven selection technique. Based on support vector selection, the proposed approach introduces a method to individually assess the suitability of each candidate impostor example for use in the background dataset. The technique can then produce a refined background datase...

Time With Children: Is More Always Better?

Exercise: Is More Always Better?

Do greater levels of exercise always promote relatively higher levels of daily energy expenditure and health? Recent studies challenge the traditional assumption that 'more exercise is better' by suggesting daily energy expenditure and health plateaus are reached beyond which incremental gains are minimal.